# Incremental Learning(Segmentation) --- > 處理時間:2022/04/23 > forked from xialeiliu/Awesome-Incremental-Learning ###### tags: `lab` # Incremental Learning / Lifelong learning ## Survey - <a name="todo"></a> Replay in Deep Learning: Current Approaches and Missing Biological Elements (**Neural Computation 2021**) [[paper](https://arxiv.org/abs/2104.04132)] - <a name="todo"></a> Online Continual Learning in Image Classification: An Empirical Survey (**Neurocomputing 2021**) [[paper](https://arxiv.org/abs/2101.10423)] [[code](https://github.com/RaptorMai/online-continual-learning)] - <a name="todo"></a> Continual Lifelong Learning in Natural Language Processing: A Survey (**COLING 2020**) [[paper](https://www.aclweb.org/anthology/2020.coling-main.574/)] - <a name="todo"></a> Class-incremental learning: survey and performance evaluation (**arXiv 2020**) [[paper](https://arxiv.org/abs/2010.15277)] [[code](https://github.com/mmasana/FACIL)] - <a name="todo"></a> A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (**Neural Networks**) [[paper](https://arxiv.org/abs/2011.01844)] [[code](https://github.com/EdenBelouadah/class-incremental-learning/tree/master/cil)] - <a name="todo"></a> A continual learning survey: Defying forgetting in classification tasks (**TPAMI 2021**) [[paper]](https://ieeexplore.ieee.org/abstract/document/9349197) [[arxiv](https://arxiv.org/pdf/1909.08383.pdf)] - <a name="todo"></a> Continual Lifelong Learning with Neural Networks: A Review (**Neural Networks**) [[paper](https://arxiv.org/abs/1802.07569)] - <a name="todo"></a> Three scenarios for continual learning (**arXiv 2019**) [[paper](https://arxiv.org/abs/1904.07734v1)][[code](https://github.com/GMvandeVen/continual-learning)] --- # Papers(共分成三類) ## ==Semantic segmentation== ### 2022 * Representation Compensation Networks for Continual Semantic Segmentation (CVPR2022)[[paper]](https://arxiv.org/abs/2203.05402) * Self-training for class-incremental semantic segmentation (TNNLS2022)[[paper]](https://arxiv.org/abs/2012.03362) ### 2021 - <a name="todo"></a> Multi-Domain Incremental Learning for Semantic Segmentation (**CVPR 2021**) [[paper](https://arxiv.org/abs/2110.12205)] - <a name="todo"></a> SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning (**NeurIPS2021**) [[paper](https://proceedings.neurips.cc/paper/2021/file/5a9542c773018268fc6271f7afeea969-Paper.pdf)] - <a name="todo"></a> RECALL: Replay-based Continual Learning in Semantic Segmentation (**ICCV, 2021**) [[paper](https://arxiv.org/pdf/2108.03673.pdf)] - <a name="todo"></a> PLOP: Learning without Forgetting for Continual Semantic Segmentation (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2011.11390)] - <a name="todo"></a> Unsupervised Model Adaptation for Continual Semantic Segmentation(**AAAI, 2021**) [[paper](https://arxiv.org/abs/2009.12518)] - <a name="todo"></a> Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging (**2021**) [[paper](https://www.nature.com/articles/s41467-021-25858-z)] - <a name="todo"></a> Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Volpi_Continual_Adaptation_of_Visual_Representations_via_Domain_Randomization_and_Meta-Learning_CVPR_2021_paper.pdf)] - <a name="todo"></a> Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.06342)] - <a name="todo"></a> A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation(**AAAI, 2021**) [[paper](https://www.aaai.org/AAAI21Papers/AAAI-2989.ZhengE.pdf)] ### 2020 - <a name="todo"></a> Continual Class Incremental Learning for CT Thoracic Segmentation(**2020**) [[paper](https://arxiv.org/abs/2008.05557)] - <a name="todo"></a> Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference (**ECCV2020**) [[paper](https://arxiv.org/abs/2007.12540)] - <a name="todo"></a> Modeling the Background for Incremental Learning in Semantic Segmentation (**CVPR2020**) [[paper](https://arxiv.org/pdf/2002.00718.pdf)] ### 2019 ### 2018 - <a name="todo"></a> Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights (**ECCV2018**) [[paper](https://arxiv.org/abs/1801.06519)] [[code](https://github.com/arunmallya/piggyback)] - <a name="todo"></a> Example Mining for Incremental Learning in Medical Imaging (**CVPR2018**)[[paper](https://arxiv.org/abs/1807.08942)] --- ## ==Instance segmentation== ### 2022 ### 2021 - <a name="todo"></a> Incremental learning for exudate and hemorrhage segmentation on fundus images (**2021**) [[paper](https://www.sciencedirect.com/science/article/pii/S1566253521000427)] - <a name="todo"></a> Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting (**IEEE, 2021**) [[paper](https://ieeexplore.ieee.org/document/9613885)] - <a name="todo"></a> Incremental Few-Shot Instance Segmentation (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2105.05312)] - <a name="todo"></a> Class-Incremental Instance Segmentation via Multi-Teacher Networks (**AAAI, 2021**) [[paper](https://see.xidian.edu.cn/faculty/chdeng/Welcome%20to%20Cheng%20Deng's%20Homepage_files/Papers/Conference/AAAI2021_Yanan.pdf)] ### 2020 ### 2019 ### 2018 --- ## ==其他== ### 2022 * Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data (CVPR2022)[[paper]](https://arxiv.org/abs/2003.08798) [[code]](https://github.com/JosephKJ/iOD) * General Incremental Learning with Domain-aware Categorical Representations (CVPR2022) [[paper]](https://arxiv.org/abs/2204.04078) * Constrained Few-shot Class-incremental Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2203.16588) * Overcoming Catastrophic Forgetting in Incremental Object Detectionvia Elastic Response Distillation (CVPR2022) [[paper]](https://arxiv.org/abs/2204.02136) * Class-Incremental Learning with Strong Pre-trained Models (CVPR2022)[[paper]](https://arxiv.org/abs/2204.03634) * Energy-based Latent Aligner for Incremental Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2203.14952) [[code]](https://github.com/JosephKJ/ELI) * Meta-attention for ViT-backed Continual Learning (CVPR2022) [[paper]](https://arxiv.org/abs/2203.11684) [[code]](https://github.com/zju-vipa/MEAT-TIL) * Learning to Prompt for Continual Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2112.08654) [[code]](https://github.com/google-research/l2p) * On Generalizing Beyond Domains in Cross-Domain Continual Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2203.03970) * Probing Representation Forgetting in Supervised and Unsupervised Continual Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2203.13381) * Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022)[[paper]](https://arxiv.org/abs/2203.00867) [[code]](https://github.com/DQiaole/ZITS_inpainting) * Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2112.04731) [[code]](https://github.com/Yujun-Shi/CwD) * Forward Compatible Few-Shot Class-Incremental Learning (CVPR2022)[[paper]](https://arxiv.org/abs/2203.06953) [[code]](https://github.com/Yujun-Shi/CwD) * Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning (CVPR2022) [[paper]](https://arxiv.org/abs/2203.06359) * DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion (CVPR2022)[[paper]](https://arxiv.org/abs/2111.11326) * Federated Class-Incremental Learning (CVPR2022)[[code]](https://github.com/conditionWang/FCIL) * Learngene: From Open-World to Your Learning Task (AAAI2022)[[paper]](https://arxiv.org/pdf/2106.06788.pdf) [[code]](https://github.com/BruceQFWang/learngene) * MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning (TPAMI2022)[[paper]](https://ieeexplore.ieee.org/abstract/document/9645290) * Rethinking the Representational Continuity: Towards Unsupervised Continual Learning (ICLR2022) [[paper]](https://openreview.net/pdf?id=9Hrka5PA7LW) * Continual Learning with Filter Atom Swapping (ICLR2022)[[paper]](https://openreview.net/pdf?id=metRpM4Zrcb) * Continual Learning with Recursive Gradient Optimization (ICLR2022) [[paper]](https://openreview.net/pdf?id=7YDLgf9_zgm) * TRGP: Trust Region Gradient Projection for Continual Learning (ICLR2022) [[paper]](https://openreview.net/pdf?id=iEvAf8i6JjO) * Looking Back on Learned Experiences For Class/task Incremental Learning (ICLR2022) [[paper]](https://openreview.net/pdf?id=RxplU3vmBx) * Continual Normalization: Rethinking Batch Normalization for Online Continual Learning (ICLR2022)[[paper]](https://openreview.net/pdf?id=vwLLQ-HwqhZ) * Model Zoo: A Growing Brain That Learns Continually (ICLR2022)[[paper]](https://openreview.net/pdf?id=WfvgGBcgbE7) * Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting (ICLR2022) [[paper]](https://openreview.net/pdf?id=tFgdrQbbaa) * Memory Replay with Data Compression for Continual Learning (ICLR2022)[[paper]](https://openreview.net/pdf?id=a7H7OucbWaU) * Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System (ICLR2022)[[paper]](https://openreview.net/pdf?id=uxxFrDwrE7Y) * Online Coreset Selection for Rehearsal-based Continual Learning (ICLR2022) [[paper]](https://openreview.net/pdf?id=f9D-5WNG4Nv) * Pretrained Language Model in Continual Learning: A Comparative Study (ICLR2022) [[paper]](https://openreview.net/pdf?id=figzpGMrdD) * Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR2022) [[paper]](https://openreview.net/pdf?id=nrGGfMbY_qK) * New Insights on Reducing Abrupt Representation Change in Online Continual Learning (ICLR2022) [[paper]](https://openreview.net/pdf?id=N8MaByOzUfb) * Towards Continual Knowledge Learning of Language Models (ICLR2022)[[paper]](https://openreview.net/pdf?id=vfsRB5MImo9) * CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability (ICLR2022) [[paper]](https://openreview.net/pdf?id=rHMaBYbkkRJ) * CoMPS: Continual Meta Policy Search (ICLR2022)[[paper]](https://openreview.net/pdf?id=PVJ6j87gOHz) * Information-theoretic Online Memory Selection for Continual Learning (ICLR2022)[[paper]](https://openreview.net/pdf?id=IpctgL7khPp) * Subspace Regularizers for Few-Shot Class Incremental Learning (ICLR2022)[[paper]](https://openreview.net/pdf?id=boJy41J-tnQ) * LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5 (ICLR2022)[[paper]](https://openreview.net/pdf?id=HCRVf71PMF) * Effect of scale on catastrophic forgetting in neural networks (ICLR2022)[[paper]]( https://openreview.net/pdf?id=GhVS8_yPeEa) * Dataset Knowledge Transfer for Class-Incremental Learning without Memory (WACV2022)[[paper]](https://arxiv.org/pdf/2110.08421.pdf) * Knowledge Capture and Replay for Continual Learning (WACV2022)[[paper]](https://openaccess.thecvf.com/content/WACV2022/papers/Gopalakrishnan_Knowledge_Capture_and_Replay_for_Continual_Learning_WACV_2022_paper.pdf) * Online Continual Learning via Candidates Voting (WACV2022)[[paper]](https://openaccess.thecvf.com/content/WACV2022/papers/He_Online_Continual_Learning_via_Candidates_Voting_WACV_2022_paper.pdf) ### 2021 - <a name="todo"></a> Dataset Knowledge Transfer for Class-Incremental Learning without Memory (**CVPR 2021**) [[paper](https://arxiv.org/abs/2110.08421)] - <a name="todo"></a> Incremental Learning for Dermatological Imaging Modality Classification (**2021**) [[paper](https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwiB1sPig431AhWLGaYKHdqIDosQFnoECAsQAQ&url=https%3A%2F%2Fwww.mdpi.com%2F2313-433X%2F7%2F9%2F180%2Fpdf&usg=AOvVaw3d-dTmq81KSNfZQI3po2gg )] - <a name="todo"></a> Incremental Object Detection via Meta-Learning (**TPAMI 2021**) [[paper](https://arxiv.org/abs/2003.08798)] [[code](https://github.com/JosephKJ/iOD)] - <a name="todo"></a> Class-Incremental Learning via Dual Augmentation (**NeurIPS2021**) [[paper](https://papers.nips.cc/paper/2021/file/77ee3bc58ce560b86c2b59363281e914-Paper.pdf)] - <a name="todo"></a> RMM: Reinforced Memory Management for Class-Incremental Learning (**NeurIPS2021**) [[paper](https://proceedings.neurips.cc/paper/2021/hash/1cbcaa5abbb6b70f378a3a03d0c26386-Abstract.html)] - <a name="todo"></a> Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=ALvt7nXa2q)] - <a name="todo"></a> Lifelong Domain Adaptation via Consolidated Internal Distribution (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=lpW-UP8VKcg)] - <a name="todo"></a> AFEC: Active Forgetting of Negative Transfer in Continual Learning (**NeurIPS2021**) [[paper](https://arxiv.org/pdf/2110.12187.pdf)] - <a name="todo"></a> Natural continual learning: success is a journey, not (just) a destination (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=W9250bXDgpK)] - <a name="todo"></a> Gradient-based Editing of Memory Examples for Online Task-free Continual Learning (**NeurIPS2021**) [[paper](https://papers.nips.cc/paper/2021/hash/f45a1078feb35de77d26b3f7a52ef502-Abstract.html)] - <a name="todo"></a> Optimizing Reusable Knowledge for Continual Learning via Metalearning (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=hHTctAv9Lvh)] - <a name="todo"></a> Formalizing the Generalization-Forgetting Trade-off in Continual Learning (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=u1XV9BPAB9)] - <a name="todo"></a> Learning where to learn: Gradient sparsity in meta and continual learning (**NeurIPS2021**) [[paper](https://arxiv.org/abs/2110.14402)] - <a name="todo"></a> Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=q1eCa1kMfDd)] - <a name="todo"></a> Posterior Meta-Replay for Continual Learning (**NeurIPS2021**) [[paper](https://arxiv.org/abs/2103.01133)] - <a name="todo"></a> Continual Auxiliary Task Learning (**NeurIPS2021**) [[paper](https://openreview.net/forum?id=EpL9IFAMa3)] - <a name="todo"></a> Mitigating Forgetting in Online Continual Learning with Neuron Calibration (**NeurIPS2021**) [[paper](https://openreview.net/pdf/cc3ebd7a4834a4551e0b1f825969f9f51fd06415.pdf)] - <a name="todo"></a> BNS: Building Network Structures Dynamically for Continual Learning (**NeurIPS2021**) [[paper](https://papers.nips.cc/paper/2021/hash/ac64504cc249b070772848642cffe6ff-Abstract.html)] - <a name="todo"></a> DualNet: Continual Learning, Fast and Slow (**NeurIPS2021**) [[paper](https://openreview.net/pdf?id=eQ7Kh-QeWnO)] - <a name="todo"></a> BooVAE: Boosting Approach for Continual Learning of VAE (**NeurIPS2021**) [[paper](https://papers.nips.cc/paper/2021/hash/952285b9b7e7a1be5aa7849f32ffff05-Abstract.html)] - <a name="todo"></a> Generative vs. Discriminative: Rethinking The Meta-Continual Learning (**NeurIPS2021**) [[paper](https://papers.nips.cc/paper/2021/hash/b4e267d84075f66ebd967d95331fcc03-Abstract.html)] - <a name="todo"></a> Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (**NeurIPS2021**) [[paper](https://papers.nips.cc/paper/2021/hash/bcd0049c35799cdf57d06eaf2eb3cff6-Abstract.html)] - <a name="todo"></a> Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection (**NeurIPS, 2021**) [[paper](https://papers.nips.cc/paper/2021/file/ffc58105bf6f8a91aba0fa2d99e6f106-Paper.pdf)] - <a name="todo"></a> SS-IL: Separated Softmax for Incremental Learning (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Ahn_SS-IL_Separated_Softmax_for_Incremental_Learning_ICCV_2021_paper.pdf)] - <a name="todo"></a> Striking a Balance between Stability and Plasticity for Class-Incremental Learning (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Striking_a_Balance_Between_Stability_and_Plasticity_for_Class-Incremental_Learning_ICCV_2021_paper.pdf)] - <a name="todo"></a> Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Cheraghian_Synthesized_Feature_Based_Few-Shot_Class-Incremental_Learning_on_a_Mixture_of_ICCV_2021_paper.pdf)] - <a name="todo"></a> Class-Incremental Learning for Action Recognition in Videos (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Park_Class-Incremental_Learning_for_Action_Recognition_in_Videos_ICCV_2021_paper.pdf)] - <a name="todo"></a> Continual Prototype Evolution:Learning Online from Non-Stationary Data Streams (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/De_Lange_Continual_Prototype_Evolution_Learning_Online_From_Non-Stationary_Data_Streams_ICCV_2021_paper.pdf)] - <a name="todo"></a> Rehearsal Revealed: The Limits and Merits of Revisiting Samples in Continual Learning (**ICCV, 2021**) [[paper](https://arxiv.org/abs/2104.07446)] - <a name="todo"></a> Co2L: Contrastive Continual Learning (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Cha_Co2L_Contrastive_Continual_Learning_ICCV_2021_paper.pdf)] - <a name="todo"></a> Wanderlust: Online Continual Object Detection in the Real World (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_Wanderlust_Online_Continual_Object_Detection_in_the_Real_World_ICCV_2021_paper.pdf)] - <a name="todo"></a> Continual Learning on Noisy Data Streams via Self-Purified Replay (**ICCV, 2021**) [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_Continual_Learning_on_Noisy_Data_Streams_via_Self-Purified_Replay_ICCV_2021_paper.pdf)] - <a name="todo"></a> Detection and Continual Learning of Novel Face Presentation Attacks (**ICCV, 2021**) [[paper](https://arxiv.org/pdf/2108.12081.pdf)] - <a name="todo"></a> Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data (**ICCV, 2021**) [[paper](https://arxiv.org/abs/2108.09020)] - <a name="todo"></a> Continual Learning for Image-Based Camera Localization (**ICCV, 2021**) [[paper](https://arxiv.org/abs/2108.09112)] - <a name="todo"></a> Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting (**ICCV, 2021**) [[paper](https://arxiv.org/abs/2108.08165)] - <a name="todo"></a> Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning (**ICCV, 2021**) [[paper](https://arxiv.org/abs/2106.09701)] - <a name="todo"></a> Few-Shot and Continual Learning with Attentive Independent Mechanisms (**ICCV, 2021**) [[paper](https://arxiv.org/abs/2107.14053)] - <a name="todo"></a> Learning with Selective Forgetting (**IJCAI, 2021**) [[paper](https://www.ijcai.org/proceedings/2021/0137.pdf)] - <a name="todo"></a> Continuous Coordination As a Realistic Scenario for Lifelong Learning (**ICML, 2021**) [[paper](https://arxiv.org/pdf/2103.03216.pdf)] - <a name="todo"></a> Kernel Continual Learning (**ICML, 2021**) [[paper](https://proceedings.mlr.press/v139/derakhshani21a.html)] - <a name="todo"></a> Variational Auto-Regressive Gaussian Processes for Continual Learning (**ICML, 2021**) [[paper](https://proceedings.mlr.press/v139/kapoor21b.html)] - <a name="todo"></a> Bayesian Structural Adaptation for Continual Learning (**ICML, 2021**) [[paper](https://proceedings.mlr.press/v139/kumar21a.html)] - <a name="todo"></a> Continual Learning in the Teacher-Student Setup: Impact of Task Similarity (**ICML, 2021**) [[paper](https://proceedings.mlr.press/v139/lee21e.html)] - <a name="todo"></a> Continuous Coordination As a Realistic Scenario for Lifelong Learning (**ICML, 2021**) [[paper](https://proceedings.mlr.press/v139/nekoei21a.html)] - <a name="todo"></a> Federated Continual Learning with Weighted Inter-client Transfer (**ICML, 2021**) [[paper](http://proceedings.mlr.press/v139/yoon21b/yoon21b.pdf)] - <a name="todo"></a> Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (**NAACL, 2021**) [[paper](https://www.aclweb.org/anthology/2021.naacl-main.378.pdf)] - <a name="todo"></a> Continual Learning for Text Classification with Information Disentanglement Based Regularization (**NAACL, 2021**) [[paper](https://www.aclweb.org/anthology/2021.naacl-main.218.pdf)] - <a name="todo"></a> CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (**EMNLP, 2021**) [[paper](https://aclanthology.org/2021.emnlp-main.550/)][[code](https://github.com/ZixuanKe/PyContinual)] - <a name="todo"></a> Co-Transport for Class-Incremental Learning (**ACM MM, 2021**) [[paper](https://arxiv.org/pdf/2107.12654.pdf)] - <a name="todo"></a> Towards Open World Object Detection (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Joseph_Towards_Open_World_Object_Detection_CVPR_2021_paper.pdf)] [[code](https://github.com/JosephKJ/OWOD)] [[video](https://www.youtube.com/watch?v=aB2ZFAR-OZg)] - <a name="todo"></a> Prototype Augmentation and Self-Supervision for Incremental Learning (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhu_Prototype_Augmentation_and_Self-Supervision_for_Incremental_Learning_CVPR_2021_paper.pdf)] - <a name="todo"></a> ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_ORDisCo_Effective_and_Efficient_Usage_of_Incremental_Unlabeled_Data_for_CVPR_2021_paper.pdf)] - <a name="todo"></a> Incremental Learning via Rate Reduction (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Wu_Incremental_Learning_via_Rate_Reduction_CVPR_2021_paper.pdf)] - <a name="todo"></a> IIRC: Incremental Implicitly-Refined Classification (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Abdelsalam_IIRC_Incremental_Implicitly-Refined_Classification_CVPR_2021_paper.pdf)] - <a name="todo"></a> Image De-raining via Continual Learning (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhou_Image_De-Raining_via_Continual_Learning_CVPR_2021_paper.pdf)] - <a name="todo"></a> Continual Learning via Bit-Level Information Preserving (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Shi_Continual_Learning_via_Bit-Level_Information_Preserving_CVPR_2021_paper.pdf)] - <a name="todo"></a> Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhai_Hyper-LifelongGAN_Scalable_Lifelong_Learning_for_Image_Conditioned_Generation_CVPR_2021_paper.pdf)] - <a name="todo"></a> Lifelong Person Re-Identification via Adaptive Knowledge Accumulation (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Pu_Lifelong_Person_Re-Identification_via_Adaptive_Knowledge_Accumulation_CVPR_2021_paper.pdf)] - <a name="todo"></a> Distilling Causal Effect of Data in Class-Incremental Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.01737)] - <a name="todo"></a> Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning (**CVPR, 2021**) [[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhu_Self-Promoted_Prototype_Refinement_for_Few-Shot_Class-Incremental_Learning_CVPR_2021_paper.pdf)] - <a name="todo"></a> Layerwise Optimization by Gradient Decomposition for Continual Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2105.07561)] - <a name="todo"></a> Adaptive Aggregation Networks for Class-Incremental Learning (**CVPR, 2021**) [[paper](https://arxiv.org/pdf/2010.05063.pdf)] - <a name="todo"></a> Efficient Feature Transformations for Discriminative and Generative Continual Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.13558)] - <a name="todo"></a> On Learning the Geodesic Path for Incremental Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2104.08572)] - <a name="todo"></a> Few-Shot Incremental Learning with Continually Evolved Classifiers (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2104.03047)] - <a name="todo"></a> Rectification-based Knowledge Retention for Continual Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.16597)] - <a name="todo"></a> DER: Dynamically Expandable Representation for Class Incremental Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.16788)] - <a name="todo"></a> Rainbow Memory: Continual Learning with a Memory of Diverse Samples (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.17230)] - <a name="todo"></a> Training Networks in Null Space of Feature Covariance for Continual Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.07113)] - <a name="todo"></a> Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning (**CVPR, 2021**) [[paper](https://arxiv.org/abs/2103.04059)] - <a name="todo"></a> Online Class-Incremental Continual Learning with Adversarial Shapley Value(**AAAI, 2021**) [[paper](https://arxiv.org/abs/2009.00093)] [[code](https://github.com/RaptorMai/online-continual-learning)] - <a name="todo"></a> Online Class-Incremental Continual Learning with Adversarial Shapley Value(**AAAI, 2021**) [[paper](https://arxiv.org/abs/2009.00093)] [[code](https://github.com/RaptorMai/online-continual-learning)] - <a name="todo"></a> Lifelong and Continual Learning Dialogue Systems: Learning during Conversation(**AAAI, 2021**) [[paper](https://www.cs.uic.edu/~liub/publications/LINC_paper_AAAI_2021_camera_ready.pdf)] - <a name="todo"></a> Continual learning for named entity recognition(**AAAI, 2021**) [[paper](https://www.amazon.science/publications/continual-learning-for-named-entity-recognition)] - <a name="todo"></a> Using Hindsight to Anchor Past Knowledge in Continual Learning(**AAAI, 2021**) [[paper](https://arxiv.org/abs/2002.08165)] - <a name="todo"></a> Curriculum-Meta Learning for Order-Robust Continual Relation Extraction(**AAAI, 2021**) [[paper](https://arxiv.org/abs/2101.01926)] - <a name="todo"></a> Continual Learning by Using Information of Each Class Holistically(**AAAI, 2021**) [[paper](https://www.cs.uic.edu/~liub/publications/AAAI2021_PCL.pdf)] - <a name="todo"></a> Gradient Regularized Contrastive Learning for Continual Domain Adaptation(**AAAI, 2021**) [[paper](https://arxiv.org/abs/2007.12942)] - <a name="todo"></a> Do Not Forget to Attend to Uncertainty While Mitigating Catastrophic Forgetting(**WACV, 2021**) [[paper](https://openaccess.thecvf.com/content/WACV2021/html/Kurmi_Do_Not_Forget_to_Attend_to_Uncertainty_While_Mitigating_Catastrophic_WACV_2021_paper.html)] - <a name="todo"></a> Class-Incremental Few-Shot Object Detection(**arXiv 2021**) [[paper](https://arxiv.org/abs/2105.07637)] - <a name="todo"></a> Continual Representation Learning for Biometric Identification(**WACV 2021**) [[paper](https://arxiv.org/abs/2006.04455)][[code](https://github.com/PatrickZH/Continual-Representation-Learning-for-Biometric-Identification)] - <a name="todo"></a> SID: Incremental learning for anchor-free object detection via Selective and Inter-related Distillation(**CVIU 2021**) [[paper](https://arxiv.org/abs/2012.15439)][[code]] - <a name="todo"></a> Meta-Learning Based Incremental Few-Shot Object Detection (**TCSVT 2021**) [[paper](https://ieeexplore.ieee.org/document/9452164)] ### 2020 - <a name="todo"></a> Rethinking Experience Replay: a Bag of Tricks for Continual Learning(**ICPR, 2020**) [[paper](https://arxiv.org/abs/2010.05595)] [[code](https://github.com/hastings24/rethinking_er)] - <a name="todo"></a> Continual Learning for Natural Language Generation in Task-oriented Dialog Systems(**EMNLP, 2020**) [[paper](https://arxiv.org/abs/2010.00910)] - <a name="todo"></a> Distill and Replay for Continual Language Learning(**COLING, 2020**) [[paper](https://www.aclweb.org/anthology/2020.coling-main.318.pdf)] - <a name="todo"></a> Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (**NeurIPS2020**) [[paper](https://proceedings.neurips.cc/paper/2020/file/d7488039246a405baf6a7cbc3613a56f-Paper.pdf)] [[code](https://github.com/ZixuanKe/CAT)] - <a name="todo"></a> Meta-Consolidation for Continual Learning (**NeurIPS2020**) [[paper](https://arxiv.org/abs/2010.00352?context=cs)] - <a name="todo"></a> Understanding the Role of Training Regimes in Continual Learning (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2006.06958.pdf)] - <a name="todo"></a> Continual Learning with Node-Importance based Adaptive Group Sparse Regularization (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2003.13726.pdf)] - <a name="todo"></a> Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2003.05856.pdf)] - <a name="todo"></a> Coresets via Bilevel Optimization for Continual Learning and Streaming (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2006.03875.pdf)] - <a name="todo"></a> RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2007.06271.pdf)] - <a name="todo"></a> Continual Deep Learning by Functional Regularisation of Memorable Past (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2004.14070.pdf)] - <a name="todo"></a> Dark Experience for General Continual Learning: a Strong, Simple Baseline (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2004.07211.pdf)] [[code](https://github.com/aimagelab/mammoth)] - <a name="todo"></a> GAN Memory with No Forgetting (**NeurIPS2020**) [[paper](https://arxiv.org/pdf/2006.07543.pdf)] - <a name="todo"></a> Calibrating CNNs for Lifelong Learning (**NeurIPS2020**) [[paper](http://people.ee.duke.edu/~lcarin/Final_Calibration_Incremental_Learning_NeurIPS_2020.pdf)] - <a name="todo"></a> Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization (**NeurIPS2020**) [[paper](https://papers.nips.cc/paper/2020/file/ca4b5656b7e193e6bb9064c672ac8dce-Paper.pdf)] - <a name="todo"></a> ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation(**RecSys, 2020**) [[paper](https://arxiv.org/abs/2007.12000)] - <a name="todo"></a> Initial Classifier Weights Replay for Memoryless Class Incremental Learning (**BMVC2020**) [[paper](https://arxiv.org/pdf/2008.13710.pdf)] - <a name="todo"></a> Adversarial Continual Learning (**ECCV2020**) [[paper](https://arxiv.org/abs/2003.09553)] [[code](https://github.com/facebookresearch/Adversarial-Continual-Learning)] - <a name="todo"></a> REMIND Your Neural Network to Prevent Catastrophic Forgetting (**ECCV2020**) [[paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123530460.pdf)] [[code](https://github.com/tyler-hayes/REMIND)] - <a name="todo"></a> Incremental Meta-Learning via Indirect Discriminant Alignment (**ECCV2020**) [[paper](https://arxiv.org/abs/2002.04162)] - <a name="todo"></a> Memory-Efficient Incremental Learning Through Feature Adaptation (**ECCV2020**) [[paper](https://arxiv.org/abs/2004.00713)] - <a name="todo"></a> PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning (**ECCV2020**) [[paper](https://arxiv.org/abs/2004.13513)] [[code](https://github.com/arthurdouillard/incremental_learning.pytorch)] - <a name="todo"></a> Learning latent representions across multiple data domains using Lifelong VAEGAN (**ECCV2020**) [[paper](https://arxiv.org/abs/2007.10221)] - <a name="todo"></a> Online Continual Learning under Extreme Memory Constraints (**ECCV2020**) [[paper](https://arxiv.org/abs/2008.01510)] - <a name="todo"></a> Class-Incremental Domain Adaptation (**ECCV2020**) [[paper](https://arxiv.org/abs/2008.01389)] - <a name="todo"></a> More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning (**ECCV2020**) [[paper](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123710698.pdf)] - <a name="todo"></a> Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation (**ECCV2020**) [[paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123660392.pdf)] - <a name="todo"></a> GDumb: A Simple Approach that Questions Our Progress in Continual Learning (**ECCV2020**) [[paper](http://www.robots.ox.ac.uk/~tvg/publications/2020/gdumb.pdf)] - <a name="todo"></a> Imbalanced Continual Learning with Partitioning Reservoir Sampling (**ECCV2020**) [[paper](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123580409.pdf)] - <a name="todo"></a> Topology-Preserving Class-Incremental Learning (**ECCV2020**) [[paper](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123640256.pdf)] - <a name="todo"></a> GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems (**CIKM2020**) [[paper](https://arxiv.org/abs/2008.13517)] - <a name="todo"></a> OvA-INN: Continual Learning with Invertible Neural Networks (**IJCNN2020**) [[paper](https://arxiv.org/abs/2006.13772)] - <a name="todo"></a> XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning (**ICLM2020**) [[paper](https://arxiv.org/pdf/2003.08561.pdf)] - <a name="todo"></a> Optimal Continual Learning has Perfect Memory and is NP-HARD (**ICML2020**) [[paper](https://arxiv.org/pdf/2006.05188.pdf)] - <a name="todo"></a> Neural Topic Modeling with Continual Lifelong Learning (**ICML2020**) [[paper](https://arxiv.org/pdf/2006.10909.pdf)] - <a name="todo"></a> Continual Learning with Knowledge Transfer for Sentiment Classification (**ECML-PKDD2020**) [[paper](https://www.cs.uic.edu/~liub/publications/ECML-PKDD-2020.pdf)] [[code](https://github.com/ZixuanKe/LifelongSentClass)] - <a name="todo"></a> Semantic Drift Compensation for Class-Incremental Learning (**CVPR2020**) [[paper](https://arxiv.org/pdf/2004.00440.pdf)] [[code](https://github.com/yulu0724/SDC-IL)] - <a name="todo"></a> Few-Shot Class-Incremental Learning (**CVPR2020**) [[paper](https://arxiv.org/pdf/2004.10956.pdf)] - <a name="todo"></a> Incremental Few-Shot Object Detection (**CVPR2020**) [[paper](https://arxiv.org/pdf/2003.04668.pdf)] - <a name="todo"></a> Incremental Learning In Online Scenario (**CVPR2020**) [[paper](https://arxiv.org/pdf/2003.13191.pdf)] - <a name="todo"></a> Maintaining Discrimination and Fairness in Class Incremental Learning (**CVPR2020**) [[paper](https://arxiv.org/pdf/1911.07053.pdf)] - <a name="todo"></a> Conditional Channel Gated Networks for Task-Aware Continual Learning (**CVPR2020**) [[paper](https://arxiv.org/pdf/2004.00070.pdf)] - <a name="todo"></a> Continual Learning with Extended Kronecker-factored Approximate Curvature (**CVPR2020**) [[paper](https://arxiv.org/abs/2004.07507)] - <a name="todo"></a> iTAML : An Incremental Task-Agnostic Meta-learning Approach (**CVPR2020**) [[paper](https://arxiv.org/pdf/2003.11652.pdf)] [[code](https://github.com/brjathu/iTAML)] - <a name="todo"></a> Mnemonics Training: Multi-Class Incremental Learning without Forgetting (**CVPR2020**) [[paper](https://arxiv.org/pdf/2002.10211.pdf)] [[code](https://github.com/yaoyao-liu/mnemonics)] - <a name="todo"></a> ScaIL: Classifier Weights Scaling for Class Incremental Learning (**WACV2020**) [[paper](https://arxiv.org/abs/2001.05755)] - <a name="todo"></a> Brain-inspired replay for continual learning with artificial neural networks (**Natrue Communications 2020**) [[paper](https://www.nature.com/articles/s41467-020-17866-2)] [[code](https://github.com/GMvandeVen/brain-inspired-replay)] - <a name="todo"></a> Learning to Continually Learn (**ECAI 2020**) [[paper](https://arxiv.org/abs/2002.09571)] [[code](https://github.com/uvm-neurobotics-lab/ANML)] - <a name="todo"></a> IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (**TNNLS 2020**) [[paper](https://ieeexplore.ieee.org/abstract/document/9127478?casa_token=-m06CQ_a7MMAAAAA:vQUc8se-NEhzal76ujhcgm4MGMozQOv0pmiyvr9OpyX4rCE9HoS83H5bZtycOY5GorcbIAKo1A)] ### 2019 - <a name="todo"></a> Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning (**CVPR2019**) [[paper](https://arxiv.org/abs/1904.03137)] - <a name="todo"></a> Learning Without Memorizing (**CVPR2019**) [[paper](https://arxiv.org/pdf/1811.08051.pdf)] - <a name="todo"></a> Learning a Unified Classifier Incrementally via Rebalancing (**CVPR2019**) [[paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Hou_Learning_a_Unified_Classifier_Incrementally_via_Rebalancing_CVPR_2019_paper.pdf)] [[code](https://github.com/hshustc/CVPR19_Incremental_Learning)] - <a name="todo"></a> Large Scale Incremental Learning (**CVPR2019**) [[paper](https://arxiv.org/abs/1905.13260)] [[code](https://github.com/wuyuebupt/LargeScaleIncrementalLearning)] - <a name="todo"></a> Continual learning of context-dependent processing in neural networks (**Nature Machine Intelligence 2019**) [[paper](https://rdcu.be/bOaa3)] [[code](https://github.com/beijixiong3510/OWM)] - <a name="todo"></a> Lifelong GAN: Continual Learning for Conditional Image Generation (**ICCV2019**) [[paper](https://arxiv.org/pdf/1907.10107.pdf)] - <a name="todo"></a> Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation (**ICCV2019**) [[paper](https://arxiv.org/pdf/1908.02984.pdf)] - <a name="todo"></a> Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild (**ICCV2019**) [[paper](https://arxiv.org/pdf/1903.12648.pdf)] - <a name="todo"></a> Meta-Learning Representations for Continual Learning (**NeurIPS2019**) [[paper](http://papers.nips.cc/paper/8458-meta-learning-representations-for-continual-learning.pdf)] [[code](https://github.com/Khurramjaved96/mrcl)] - <a name="todo"></a> Online Continual Learning with Maximal Interfered Retrieval (**NeurIPS2019**) [[paper](http://papers.neurips.cc/paper/9357-online-continual-learning-with-maximal-interfered-retrieval)] - <a name="todo"></a> Random Path Selection for Incremental Learning (**NeurIPS2019**) [[paper](https://arxiv.org/pdf/1906.01120.pdf)] - <a name="todo"></a> Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability (**KDD2019**) [[paper](http://www.lamda.nju.edu.cn/yangy/KDD19.pdf)] - <a name="todo"></a> Incremental Learning Using Conditional Adversarial Networks (**ICCV2019**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Xiang_Incremental_Learning_Using_Conditional_Adversarial_Networks_ICCV_2019_paper.html)] - <a name="todo"></a> IL2M: Class Incremental Learning With Dual Memory (**ICCV2019**) [[paper](http://openaccess.thecvf.com/content_ICCV_2019/papers/Belouadah_IL2M_Class_Incremental_Learning_With_Dual_Memory_ICCV_2019_paper.pdf)] - <a name="todo"></a> Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay (**IJCAI2019**) [[paper]](https://www.ijcai.org/Proceedings/2019/0463.pdf) - <a name="todo"></a> Compacting, Picking and Growing for Unforgetting Continual Learning (**NeurIPS2019**)[[paper](https://papers.nips.cc/paper/9518-compacting-picking-and-growing-for-unforgetting-continual-learning.pdf)][[code](https://github.com/ivclab/CPG)] - <a name="todo"></a> Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning (**ICMR2019**) [[paper](https://dl.acm.org/doi/10.1145/3323873.3325053)][[code](https://github.com/ivclab/PAE)] - <a name="todo"></a> Towards Training Recurrent Neural Networks for Lifelong Learning (**Neural Computation 2019**) [[paper](https://arxiv.org/pdf/1811.07017.pdf)] - <a name="todo"></a> Task-Free Continual Learning (**CVPR2019**) [[paper](https://arxiv.org/pdf/1812.03596.pdf)] - <a name="todo"></a> Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting (**ICML2019**) [[paper](https://arxiv.org/abs/1904.00310)] - <a name="todo"></a> Efficient Lifelong Learning with A-GEM (**ICLR2019**) [[paper](https://openreview.net/forum?id=Hkf2_sC5FX)] [[code](https://github.com/facebookresearch/agem)] - <a name="todo"></a> Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference (**ICLR2019**) [[paper](https://openreview.net/forum?id=B1gTShAct7)] [[code](https://github.com/mattriemer/mer)] - <a name="todo"></a> Overcoming Catastrophic Forgetting via Model Adaptation (**ICLR2019**) [[paper](https://openreview.net/forum?id=ryGvcoA5YX)] - <a name="todo"></a> A comprehensive, application-oriented study of catastrophic forgetting in DNNs (**ICLR2019**) [[paper](https://openreview.net/forum?id=BkloRs0qK7)] ### 2018 - <a name="todo"></a> Memory Replay GANs: learning to generate images from new categories without forgetting (**NIPS2018**) [[paper](https://arxiv.org/abs/1809.02058)] [[code](https://github.com/WuChenshen/MeRGAN)] - <a name="todo"></a> Lifelong Learning with Dynamically Expandable Networks (**ICLR2018**) [[paper](https://openreview.net/forum?id=Sk7KsfW0-)] - <a name="todo"></a> FearNet: Brain-Inspired Model for Incremental Learning (**ICLR2018**) [[paper](https://openreview.net/forum?id=SJ1Xmf-Rb)] - <a name="todo"></a> Reinforced Continual Learning (**NIPS2018**) [[paper](http://papers.nips.cc/paper/7369-reinforced-continual-learning.pdf)] [[code](https://github.com/xujinfan/Reinforced-Continual-Learning)] - <a name="todo"></a> Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting (**NIPS2018**) [[paper](http://papers.nips.cc/paper/7631-online-structured-laplace-approximations-for-overcoming-catastrophic-forgetting.pdf)] - <a name="todo"></a> Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting (R-EWC) (**ICPR2018**) [[paper](https://arxiv.org/abs/1802.02950)] [[code](https://github.com/xialeiliu/RotateNetworks)] - <a name="todo"></a> Exemplar-Supported Generative Reproduction for Class Incremental Learning (**BMVC2018**) [[paper](http://bmvc2018.org/contents/papers/0325.pdf)] [[code](https://github.com/TonyPod/ESGR)] - <a name="todo"></a> End-to-End Incremental Learning (**ECCV2018**) [[paper](https://arxiv.org/abs/1807.09536)][[code](https://github.com/fmcp/EndToEndIncrementalLearning)] - <a name="todo"></a> Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence (**ECCV2018**)[[paper](http://arxiv-export-lb.library.cornell.edu/abs/1801.10112)] - <a name="todo"></a> Memory Aware Synapses: Learning what (not) to forget (**ECCV2018**) [[paper](https://arxiv.org/abs/1711.09601)] [[code](https://github.com/rahafaljundi/MAS-Memory-Aware-Synapses)] - <a name="todo"></a> Lifelong Learning via Progressive Distillation and Retrospection (**ECCV2018**) [[paper](http://openaccess.thecvf.com/content_ECCV_2018/papers/Saihui_Hou_Progressive_Lifelong_Learning_ECCV_2018_paper.pdf)] - <a name="todo"></a> PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning (**CVPR2018**) [[paper](https://arxiv.org/abs/1711.05769)] [[code](https://github.com/arunmallya/packnet)] - <a name="todo"></a> Overcoming Catastrophic Forgetting with Hard Attention to the Task (**ICML2018**) [[paper](http://proceedings.mlr.press/v80/serra18a.html)] [[code](https://github.com/joansj/hat)] ### 2017 - <a name="todo"></a> Incremental Learning of Object Detectors Without Catastrophic Forgetting (**ICCV2017**) [[paper](http://openaccess.thecvf.com/content_iccv_2017/html/Shmelkov_Incremental_Learning_of_ICCV_2017_paper.html)] - <a name="todo"></a> Overcoming catastrophic forgetting in neural networks (EWC) (**PNAS2017**) [[paper](https://arxiv.org/abs/1612.00796)] [[code](https://github.com/ariseff/overcoming-catastrophic)] [[code](https://github.com/stokesj/EWC)] - <a name="todo"></a> Continual Learning Through Synaptic Intelligence (**ICML2017**) [[paper](http://proceedings.mlr.press/v70/zenke17a.html)] [[code](https://github.com/ganguli-lab/pathint)] - <a name="todo"></a> Gradient Episodic Memory for Continual Learning (**NIPS2017**) [[paper](https://arxiv.org/abs/1706.08840)] [[code](https://github.com/facebookresearch/GradientEpisodicMemory)] - <a name="todo"></a> iCaRL: Incremental Classifier and Representation Learning (**CVPR2017**) [[paper](https://arxiv.org/abs/1611.07725)] [[code](https://github.com/srebuffi/iCaRL)] - <a name="todo"></a> Continual Learning with Deep Generative Replay (**NIPS2017**) [[paper](https://arxiv.org/abs/1705.08690)] [[code](https://github.com/kuc2477/pytorch-deep-generative-replay)] - <a name="todo"></a> Overcoming Catastrophic Forgetting by Incremental Moment Matching (**NIPS2017**) [[paper](https://arxiv.org/abs/1703.08475)] [[code](https://github.com/btjhjeon/IMM_tensorflow)] - <a name="todo"></a> Expert Gate: Lifelong Learning with a Network of Experts (**CVPR2017**) [[paper](https://arxiv.org/abs/1611.06194)] - <a name="todo"></a> Encoder Based Lifelong Learning (**ICCV2017**) [[paper](https://arxiv.org/abs/1704.01920)] ### 2016 - <a name="todo"></a> Learning without forgetting (**ECCV2016**) [[paper](https://link.springer.com/chapter/10.1007/978-3-319-46493-0_37)] [[code](https://github.com/lizhitwo/LearningWithoutForgetting)]