๐ Table of whole paper reviews ๐๐ป link
๐ฉ๐ปโ๐ป Organization with custom implementation codes ๐๐ป link
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
ICLR | 2021 | X. Zhu and W. Su et al. | Deformable DETR: Deformable Transformers for End-to-End Object Detection | SenseTime Research, Univ. of Science and Technology of China, and The Chinese Univ. of Hong Kong | [official code] |
ICLR | 2021 | K. Choromanski, V. Likhosherstov, D. Dohan, X. Song, A. Gane, T. Sarlos, P. Hawkins, and J. Davis et al. | Rethinking Attention with Performers | Google, Univ. of Cambridge, Deepmind, and Alan Turing Institute | [official code] |
Arxiv | 2020 | S. Wang et al. | Linformer: Self-Attention with Linear Complexity | Facebook AI | - |
Arxiv | 2020 | H. Touvron et al. | Training Data-efficient Image Transformer & Distillation through Attention | Facebook AI Research (FAIR) and Sorbonne Univ. | [official code] [summary] |
Arxiv | 2020 | A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, and X. Zhai et al. | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | Google Research | [official code] [summary] |
ECCV | 2020 | N. Carion et al. | End-to-End Object Detection with Transformers | Facebook AI Research (FAIR) | [official code] [custom code] [summary] |
ICLR | 2020 | N. Kitaev and L. Kaiser et al. | Reformer: The Efficient Transformer | U.C. Berkeley and Google Research | [official code] |
NeurIPS | 2017 | A. Vaswani et al. | Attention Is All You Need | Google Brain, Google Research, and Univ. of Toronto | [official code] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
Arxiv | 2020 | K. Sohn et al. | FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | Google Research | [official code] [summary] |
CVPR | 2020 | D. Wang et al. | FocalMix: Semi-Supervised Learning for 3D Medical Image Detection | Peking University, Yizhun Medical AI | [summary] |
ICLR | 2020 | D. Berthelot et al. | ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring | Google Research and Google Cloud AI | [official code] |
NeurIPS | 2019 | D. Berthelot et al. | MixMatch: A Holistic Approach to Semi-Supervised Learning | Google Research | [official code] [summary] |
Arxiv | 2019 | Q. Xie et al. | Unsupervised Data Augmentation for Consistency Training | Google Research, Carnegie Mellon University | [official code] [summary] [ppt] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
CVPR | 2020 | S. Yun and J. Park et al. | Regularizing Class-wise Predictions via Self-knowledge Distillation | KAIST | [official code] [summary] [ppt] |
CVPR | 2020 | Y. Liu et al. | Search to Distill: Pearls are Everywhere but not the Eyes | Google AI, Google Brain | [summary] |
ICCV | 2019 | L. Zhang et al. | Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation | Tsinghua University | [official code] [summary] |
ICCV | 2019 | B. Heo et al. | A Comprehensive Overhaul of Feature Distillation | NAVER Corp, Seoul National University | [official code] |
NeurIPS | 2018 | X. Wang et al. | KDGAN: Knowledge Distillation with Generative Adversarial Networks | University of Melbourne | [official code] [summary] [ppt] |
ICML | 2018 | S. Srinivas et al. | Knowledge Transfer with Jacobian Matching | Idiap Research Institute & EPFL | [summary] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
ICLR | 2021 | T. Nguyen et al. | Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth | Google Research | - |
CVPR | 2020 | I. Radosavovic et al. | Designing Network Design Spaces | Facebook AI Research (FAIR) | [official code] [custom code] [summary] [ppt] |
CVPR | 2019 | T. He et al. | Bag of Tricks for Image Classification with Convolutional Neural Networks | Amazon Web Services | - |
ICML | 2020 | P. W. Koh, T, Nguyen, and Y. S. Tang et al. | Concept Bottleneck Models | Stanford Univ. and Google Research | [summary] |
ICML | 2019 | S. Kornblith et al. | Similarity of Neural Network Representations Revisited | Google Brain | [official code] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
Arxiv | 2019 | M. Yang et al. | Benchmarking Attribution Methods with Relative Feature Importance | Google Brain | [official code] |
NeurIPS | 2019 | S. Hooker et al. | A Benchmark for Interpretability Methods in Deep Neural Networks | Google Brain | [summary] [ppt] |
ICCV Workshop | 2019 | B. Kim et al. | Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps | KAIST | [official code] |
NeurIPS | 2018 | J. Adebayo et al. | Sanity Checks for Saliency Maps | Google Brain | - |
ICML Workshop | 2018 | J. Seo et al. | Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative | Satrec Initiative, KAIST | - |
CVPR | 2018 | Q. Zhang et al. | Interpretable Convolutional Neural Networks | University of California | [official code] |
ICCV | 2017 | R. Selvaraju et al. | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Georgia Institute of Technology | [official code] [ppt] |
CVPR | 2017 | D. Smilkov et al. | SmoothGrad: removing noise by adding noise | Google Inc. | - |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
ICCV | 2019 | S. Zhao et al. | Recursive Cascaded Networks for Unsupervised Medical Image Registration | Tsinghua Univ., Beihang Univ., and Microsoft Research | [official code] |
Journal of Biomedical and Health Informatics | 2019 | S. Zhao et al. | Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network | Tsinghua Univ., Beihang Univ., and Microsoft Research | [official code] [summary] |
CVPR, TMI | 2018 | G. Balakrishman et al. | VoxelMorph: A Learning Framework for Deformable Medical Image Registration | MIT and Cornell Univ. | [official code] [summary] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
CVPR | 2019 | J. Lee et al. | FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference | Seoul National Univ. | [summary] [ppt] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
CVPR | 2019 | J. Deng et al. | ArcFace: Additive Angular Margin Loss for Deep Face Recognition | Imperial College London, InsightFace, FaceSoft | [official code] [summary] |
CVPR | 2017 | W. Liu et al. | SphereFace: Deep Hypersphere Embedding for Face Recognition | Georgia Institute of Technology, Carnegie Mellon Univ., and Sun Yat-Sen Univ. | [official code] [summary] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
CVPR | 2020 | I. Kim and W. Baek et al. | Spatially Attentive Output Layer for Image Classification | Kakao Brain | [summary] |
ECCV | 2020 | M. KIm and J. Park et al. | Learning Visual Context by Comparison | Lunit Inc. and Seoul National Univ. Hospital | [official code] [summary] |
CVPR | 2018 | J. Hu et al. | Squeeze-and-Excitation Networks | University of Chinese Academy of Sciences | [official code] |
ECCV | 2018 | S. Woo et al. | CBAM: Convolutional Block Attention Module | KAIST | [official code] [summary] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
CVPR | 2019 | A. Kirillov et al. | Panoptic Segmentation | Facebook AI Research (FAIR) and Heidelberg Univ. | [ppt] |
ECCV | 2018 | L. Chen et al. | Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation | Google Inc. | [official code] [ppt] |
MIDL | 2018 | O. Oktay et al. | Attention U-Net: Learning Where to Look for the Pancreas | Imperial College London, Babylon Heath | [official code] |
MICCAI | 2016 | ร. รiรงek et al. | 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation | University of Freiburg | - |
MICCAI | 2015 | ร. Ronneberger et al. | U-Net: Convolutional Networks for Biomedical Image Segmentation | University of Freiburg | - |
CVPR | 2015 | J. Long et al. | Fully Convolutional Networks for Semantic Segmentation | UC Berkeley | [official code] [summary] |
ICLR | 2015 | L. Chen et al. | Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs | University of California, Google Inc., and CentraleSupelec | [official code] [summary] [ppt] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
CVPR | 2020 | G. Song et al. | Revisiting the Sibling Head in Object Detector | SenseTime X-Lab and The Chinese Univ. of Hong Kong | [official code] [summary] |
ECCV | 2020 | N. Carion et al. | End-to-End Object Detection with Transformers | Facebook AI Research (FAIR) | [official code] [custom code] [summary] |
CVPR | 2019 | H. Rezatofighi et al. | Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression | Stanford Univ., The University of Adelaide, and Aibee Inc | [ppt] |
From | Year | Authors | Paper | Institution | url |
---|---|---|---|---|---|
ICML | 2019 | M. Tan et al. | EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | Google Research | [official code] [ppt] |
CVPR | 2017 | S. Xie et al. | Aggregated Residual Transformations for Deep Neural Networks | UC San Diego | [official code] |
CVPR | 2017 | F. Chollet et al. | Xception: Deep Learning with Depthwise Separable Convolutions | Google Inc. | - |
CVPR | 2016 | K. He et al. | Deep Residual Learning for Image Recognition | Microsoft Research | [official code] summary |
ICLR | 2015 | k. Simonyan et al. | Very Deep Convolutional Networks for Large-Scale Image Recognition | University of Oxford | - |
CVPR | 2015 | C. Szegedy et al. | Going Deeper with Convolutions | Google Inc. | [ppt] |