{%hackmd @themes/dracula %}
https://www.youtube.com/watch?v=nKM9875PVtU
https://www.coursera.org/specializations/mathematics-for-machine-learning-and-data-science
d07c66cd58
https://openaccess.thecvf.com/content/WACV2024/papers/Lin_Common_Diffusion_Noise_Schedules_and_Sample_Steps_Are_Flawed_WACV_2024_paper.pdf

## Note - Books & Online Course

- [Understanding Diffusion Models: A Unified Perspective](/CUHoEaL3TdaemDKvFVT2QQ)
- [Unordered Data Structures](/OAa7H2hMSJqmFFG-VwmdaA)
- [Ordered Data Structures](/nOe9GBZGTvmPrnILrTD7GQ)
- [Object-Oriented Data Structures in C++](/Jecqg_B5QqiKIpNGEKraEQ)
- [機器學習基石 (Machine Learning Foundations)—Mathematical Foundations](/mjyW2ktIRsOUU3HgiV0dtg)
- [Machine Learning A Probabilistic Perspective](/S7zyt1lEQveBsuaTD8xfMw)
- [Google C++ Style Guide](/nAVwfIMsTwW7Yyqgnmm4kQ)
- [Google Python Style Guide](/80352oK6QZSyvXaj6j_1gA)
- [CS231n: Deep Learning for Computer Vision](/HRwjsqaET1OY_YUtdiHdWQ)
- [CS229M/STATS214: Machine Learning Theory](/bsMst8dyT5SyMJcfg1Mr9w)
- [KL](/9N_mka8eSG-UboRP4ubAeQ)

## 2023

- [Applications and Limits of Image-to-Image Translation Models](/j850sfZ-R6-xU41Fj6O9Ow)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](/GqNuSVZyQ2-pWDPHnmSriQ)
- [Diffusion in Style](/SvoOQJZhQTqESwhp8CZeCg)

## 2022

- [Vision Transformer with Deformable Attention](/2GH_C3PgRqOzMtkZJnwKnA)
- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](/HxbJJAQ9QnSGnqe08LFJrg)
- [Learning to Deblur using Light Field Generated and Real Defocus Images](/EoWqHtqHSS6mfnT76XfqzQ)
- [View-Wise Versus Cluster-Wise Weight: Which Is Better for Multi-View Clustering?](/LzBCodOjQpSxNSGOJk7Ivw)
- [Understanding Diffusion Models: A Unified Perspective](/CUHoEaL3TdaemDKvFVT2QQ)

## 2021

- [A Two-stage Deep Network for High Dynamic Range Image Reconstruction](/ROqLGZ6oT2aRiTADhH1V4g)
- [GAN-Control: Explicitly Controllable GANs](/ZnvR43NoT-upbdS3H6Tkhg)
- [IMAGE FUSION TRANSFORMER](/CR0iFuJGTfGiWdtl8TB-hQ)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](/okPRGJ8kQ5WLFvN-DJR7aQ)
- [Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks](/4IZ3rWV-RXiT0gH2vzP-IA)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](/u33J84T1S96T-Jf39FtVYA)
- [Efficiently Modeling Long Sequences with Structured State Spaces](/HoZYUIlNS52zOhw30OCwqg)
- [High-Resolution Image Synthesis with Latent Diffusion Models](/x_DX9NzyR6mrMXOm_UEYrg)

## 2020

- [GANSpace: Discovering Interpretable GAN Controls](/7IeFPU5mSHiPXhFi_xPwsQ)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](/bWZezq3hSgWsxIC94LKosw)
- [AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE](/K1AbqsyWSUyPo5SrM4x6xA)
- [Superpixel-Based Seamless Image Stitching for UAV Images](/7M22Nm4aRx2Vxo86kWKsdA)
- [ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants](/-RFWBOt8RdKeEoYrS0oKSw)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](/ewQ1xXd5SpqodlWzMWT5oA)
- [Denoising Diffusion Probabilistic Models](/flLMbEjFQKiqA7URyylZnA)
- [DENOISING DIFFUSION IMPLICIT MODELS](/YeCGmNU9R5mgWo5i9-wVCA)

## 2019

- [Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation](/Yguj-oYVT4KroJADxfjvAg)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](/RbugXuRfQbWHVdF55JglRg)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](/k2l5ekguS2CvhxZ7zBm0wg)
- [Mish: A Self Regularized Non-Monotonic Activation Function](/i7FjRHYCQKeLgT2yA80WDw)

## 2018

- [Semantic Image Synthesis with Spatially-Adaptive Normalization](/RbugXuRfQbWHVdF55JglRg)
- [DGC-Net: Dense Geometric Correspondence Network](/9cCxSaLNQ1qxyyxRdv9jrg)
- [Multi-View Clustering](/Ns2vKyDHRlKjJLM5pI3HPQ)
- [A Note on the Inception Score](/-5LXIsLJQM28bF-sAnp7Lw)

## 2017

- [DECISION-BASED ADVERSARIAL ATTACKS: RELIABLE ATTACKS AGAINST BLACK-BOX MACHINE LEARNING MODELS](/nKO9KlPjRgaEbnKFFTOb6A)
- [LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation](/caITyBYKSgapjH_l59OtpA)
- [Model Compression and Acceleration for Deep Neural Networks](/qZMNwDmZThuMvDhyWDEEeA)
- [SKIP CONNECTIONS ELIMINATE SINGULARITIES](/wLLrinq8TRu8I3826fuBVg)
- [Attention Is All You Need (Transformer)](/11069bzHTUyQU1ClW9_TMQ)
- [Parallax-Tolerant Image Stitching Based on Robust Elastic Warping](/Sks7Ahn1R6adbUddM1-pLg)
- [Unpaired Image-to-Image Translationusing Cycle-Consistent Adversarial Networks](/0Xez8cHrTDiqqAxNQqZB_g)
- [MIXED PRECISION TRAINING](/q7Jk5vYrRzyhAWyE7Ib57g)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium Martin](/3UsfaMQ7TP60ScIbYWpBZQ)

## 2016

- [Image-to-Image Translation with Conditional Adversarial Networks](/MFgtPJ5KSMeO5m5tsnSk6A)
- [Learning without Forgetting](/MzBgLWi1SwaHzL3sXdxAbA)

## 2015

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](/5DnnkWSlTc2JvEKuDCMmlQ)
- [Spatial Transformer Networks](/oOy5KcxIQGCtEgap3eIZDA)
- [Adaptive As-Natural-As-Possible Image Stitching](/CN5mVfK1SiSzYIwneO6skw)
- [Rethinking the Inception Architecture for Computer Vision](/amWhu-71S3eas3lsC5SJHA)

## 2014

- [Generative Adversarial Nets](/BZSURkLxT7yhvy7epDpO3A)
- [Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice](/h5x7ryS4Ta-2LRi_n_8wyA)

## 2013

- [Rectifier Nonlinearities Improve Neural Network Acoustic Models](/BfmTqdskTGW0mFhThzAKeg)

## 2008

- [Dynamics of Learning Near Singularities in Layered Networks](/cTdxNQ6dRDm7ws87Sq35pw)

## 2006

- [SURF: Speeded Up Robust Features](/8Z4Gi3QzQDGovzrPxS-q8g)

## 2005

- [A non-local algorithm for image denoising (NL-means)](/Kp4iDBlETfaRXwvIgjHwCQ)

## 2004

- [Distinctive Image Features from Scale-Invariant Keypoints](/-eg_wyzfQNCDwBCQ0dzBug)
- [Image quality assessment: from error visibility to structural similarity](/kaBoIxHVQ5iw305wyL-dkA)

## 1996

- [Point-Based Elastic Registration of Medical Image Data Using Approximating Thin-Plate Splines](/6fzDDbrfSUOYwQlNkObH5A)

## 1995

- [Mean Shift, Mode Seeking, and Clustering](/O4s9dsjpQ96Ikc-lxtYb0w)