Try   HackMD

paper整理-deep learning object detection

處理時間:2022/03/10
forked from xialeiliu/Awesome-Incremental-Learning

2014

  • 重要 [R-CNN] Rich feature hierarchies for accurate object detection and semantic segmentation | [CVPR' 14] |[pdf] [official code - caffe]

  • 重要 [OverFeat] OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | [ICLR' 14] |[pdf] [official code - torch]

  • 重要 [SPPnet] Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | |[pdf]

  • 重要-影像分類 [ResNet] Deep Residual Learning for Image Recognition [pdf]

  • 重要-影像分類 [VGG] Very Deep Convolutional Networks for Large-Scale Image Recognition [pdf]

2015

2016

2017

2018

2019

  • 重要 [M2Det] M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network | [AAAI' 19] |[pdf] [official code - pytorch] 、引用次數436

  • 重要 [GIoU] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression | [CVPR' 19] |[pdf] 、引用次數1233

  • 重要 [Libra R-CNN] Libra R-CNN: Towards Balanced Learning for Object Detection | [CVPR' 19] |[pdf] 、引用次數613

  • 重要 [NAS-FPN] NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection | [CVPR' 19] |[pdf] 、引用次數697

  • [Adaptive NMS] Adaptive NMS: Refining Pedestrian Detection in a Crowd | [CVPR' 19] |[pdf] 、引用次數152

  • Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection | [CVPR' 19] |[pdf]、引用次數138

  • Multi-adversarial Faster-RCNN for Unrestricted Object Detection | [ICCV' 19] |[pdf]、引用次數127

  • A Robust Learning Approach to Domain Adaptive Object Detection | [ICCV' 19] |[pdf] 、引用次數103

  • Selectivity or Invariance: Boundary-Aware Salient Object Detection | [ICCV' 19] |[pdf] 、引用次數104

  • 重要 [TridentNet] Scale-Aware Trident Networks for Object Detection | [ICCV' 19] |[pdf] 、引用次數504

  • 重要 [CenterNet] CenterNet: Keypoint Triplets for Object Detection | [ICCV' 19] |[pdf]、引用次數962

  • [Auto-FPN] Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification | [ICCV' 19] |[pdf] 、引用次數104

  • [ThunderNet] ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices | [ICCV' 19] |[pdf]、引用次數142

  • [RDN] Relation Distillation Networks for Video Object Detection | [ICCV' 19] |[pdf]、引用次數99

  • [SCAN] Stacked Cross Refinement Network for Edge-Aware Salient Object Detection | [ICCV' 19] |[official code] |[pdf]、引用次數164

  • [ClusDet] Clustered Object Detection in Aerial Images | [ICCV' 19] |[pdf]、引用次數100

  • Few-Shot Object Detection via Feature Reweighting | [ICCV' 19] |[pdf] 、引用次數281

  • [Objects365] Objects365: A Large-Scale, High-Quality Dataset for Object Detection | [ICCV' 19] |[pdf] 、引用次數104

  • 重要 [EGNet] EGNet: Edge Guidance Network for Salient Object Detection | [ICCV' 19] |[pdf] 、引用次數400

  • 重要[FCOS] FCOS: Fully Convolutional One-Stage Object Detection | [ICCV' 19] |[pdf] 、引用次數1694

  • [RepPoints] RepPoints: Point Set Representation for Object Detection | [ICCV' 19] |[pdf] 、引用次數318

  • Meta-Learning to Detect Rare Objects | [ICCV' 19] |[pdf]、引用次數117

  • [Gaussian YOLOv3] Gaussian YOLOv3: An Accurate and Fast Object Detector using Localization Uncertainty for Autonomous Driving | [ICCV' 19] |[pdf] [official code - c] 、引用次數204

  • [FreeAnchor] FreeAnchor: Learning to Match Anchors for Visual Object Detection | [NeurIPS' 19] |[pdf] 、引用次數169

  • [DetNAS] DetNAS: Backbone Search for Object Detection | [NeurIPS' 19] |[pdf] 、引用次數137

  • [AA] Learning Data Augmentation Strategies for Object Detection | [arXiv' 19] |[pdf] 、引用次數241

  • [Spinenet] Spinenet: Learning scale-permuted backbone for recognition and localization | [arXiv' 19] |[pdf] 、引用次數111

  • 重要 Object Detection in 20 Years: A Survey | [arXiv' 19] |[pdf] 、引用次數508

  • Salient Object Detection in the Deep Learning Era: An In-Depth Survey | [CVPR 19] |[pdf] 、引用次數288

  • 重要 [CSPNet] CSPNet: A New Backbone that can Enhance Learning Capability of CNN [pdf] 、引用次數736

2020

  • [CBnet] Cbnet: A novel composite backbone network architecture for object detection | [AAAI' 20] |[pdf] 、引用次數144

  • 重要 [Distance-IoU Loss] Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression | [AAAI' 20] |[pdf] 、引用次數594

  • 重要 [YOLOv4] YOLOv4: Optimal Speed and Accuracy of Object Detection | [arXiv' 20] |[pdf] 、引用次數3206

  • 重要 [Scaled-YOLOv4] Scaled-YOLOv4: Scaling Cross Stage Partial Network、[pdf] 、引用次數212

  • [PP YOLO] PP-YOLO: An Effective and Efficient Implementation of Object Detector |[pdf] 、引用次數57

  • Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector | [CVPR' 20] |[pdf] 、引用次數188

  • 重要 Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection | [CVPR' 20] |[pdf] 、引用次數369

  • Rethinking Classification and Localization for Object Detection | [CVPR' 20] |[pdf] 、引用次數133

  • 重要 [EfficientDet] EfficientDet: Scalable and Efficient Object Detection | [CVPR' 20] |[pdf] 、引用次數1498

  • Dynamic Refinement Network for Oriented and Densely Packed Object Detection | [CVPR' 20] |[pdf] 、引用次數76

  • [D2Det] D2Det: Towards High Quality Object Detection and Instance Segmentation | [CVPR' 20] |[pdf] 、引用次數71

  • Prime Sample Attention in Object Detection | [CVPR' 20] |[pdf] 、引用次數88

  • Exploring Categorical Regularization for Domain Adaptive Object Detection | [CVPR' 20] |[pdf] 、引用次數79

  • [NAS-FCOS] NAS-FCOS: Fast Neural Architecture Search for Object Detection | [CVPR' 20] |[pdf] 、引用次數79

  • [AugFPN] AugFPN: Improving Multi-Scale Feature Learning for Object Detection | [CVPR' 20] |[pdf] 、引用次數113

  • Incremental Few-Shot Object Detection | [CVPR' 20] |[pdf] 、引用次數90

  • DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution | [arXiv' 20] |[pdf] 、引用次數198

  • 重要 [DETR] End-to-End Object Detection with Transformers | [ECCV' 20] |[pdf] 、引用次數1644

  • Suppress and Balance: A Simple Gated Network for Salient Object Detection | [ECCV' 20] |[code] 、引用次數111

  • [Chained-Tracker] Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking | [ECCV' 20] |[pdf] -引用次數81

  • Highly Efficient Salient Object Detection with 100K Parameters | [ECCV' 20] |[pdf] -引用次數63

  • Arbitrary-Oriented Object Detection with Circular Smooth Label | [ECCV' 20] |[pdf] -引用次數87

  • Soft Anchor-Point Object Detection | [ECCV' 20] |[pdf] -引用次數69

  • [Dynamic R-CNN] Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training | [ECCV' 20] |[pdf] -引用次數91

  • Multi-Scale Positive Sample Refinement for Few-Shot Object Detection | [ECCV' 20] |[pdf] 、引用次數53

  • Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild | [ECCV' 20] |[pdf] 、引用次數60

  • Pillar-based Object Detection for Autonomous Driving | [ECCV' 20] |[pdf] 、引用次數52

  • Probabilistic Anchor Assignment with IoU Prediction for Object Detection | [ECCV' 20] |[pdf] 、引用次數76

  • On the Importance of Data Augmentation for Object Detection | [ECCV' 20] |[pdf] 、引用次數53

2021

  • [Generalized Focal Loss V2] Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection [pdf]、引用次數35

  • [Sparse R-CNN] Sparse R-CNN: End-to-End Object Detection with Learnable Proposals [pdf]、引用次數107

  • [Center-based 3D] Center-based 3D Object Detection and Tracking [pdf]、引用次數141

  • [YOLOR] You Only Learn One Representation: Unified Network for Multiple Tasks [pdf]、引用次數32

補充

行人檢測-整理

https://github.com/xingkongliang/Pedestrian-Detection

Last changed by 
 
LiaoZZ
Study at NSYSU-Deep Vision Lab
0
1
538

Read more

安裝 GroundingDINO、GroundingSAM

Install GroundingDINO、GroundingSAM Github: https://github.com/IDEA-Research/Grounded-Segment-Anything#installation change to install like this(every MUST same): cuda:11.6 (this need go to Nvidia web, and install finish, you can at /usr/local/cuda-11.6 to find it ! ) Python: 3.9.16 Pytorch: 1.13.1 torch vision: 0.14.1

Jun 1, 2023
LeetCode筆記

暫停更新 2022/06/24 LeetCode-Minimun Size Subarray Sum(C++版)-定洲:影片 | 筆記 2022/05/20 LeetCode-Delete Node-Linked List統整(C++版)-定洲:影片 | 筆記 2022/05/20 LeetCode-Reverse Integer(C++版)-定洲:影片 | 筆記 2022/05/06 LeetCode-Add Two Numbers(C++版)-定洲:影片 | 筆記 2022/05/06 LeetCode-Container With Most Water(C++版)-衡安:影片 | 筆記 Supplement 補充資料

Apr 20, 2023
特殊的電腦深度視覺模型

更新時間2022/08/18 LFFD(高速人臉辨識)： LFFD(原作者-MXNet版/NCNN版)-網址 LFFD(Pytorch版)-網址 LFD (一年多前提出的新版本/支援多類別)-網址 高速YOLO：

Aug 18, 2022
YOLO-Fastest訓練到部屬樹莓派Pi4

更新日期:2022/6/42 訓練: 使用darknet cfg檔請參照 https://github.com/LiaoZihZrong/yolo-fastest/blob/main/yolo-fast.cfg 轉模型 轉出我們的檔案 git clone https://github.com/LiaoZihZrong/weight-Yolo-fastest-model-h5

Jun 24, 2022
Read more from LiaoZZ
Published on HackMD