这个项目是用来对前两年读过的论文做一下整理，回顾本科期间所阅读过的论文。同时也整理之后要读的论文，均给出了论文链接以及代码，其中文本图像生成是一个大专题，比较完整，整理后放在了./text2image/README.md文件中。
本人本科期间主要从事人工智能在图像处理上的应用，在图像增强上有做过单图超分（Single Image Super-Resolution， SISR），单图去雨（Single Image Deraining），图神经网络（Graph Convolutional Networks， GCNs）以及跨模态图像文本生成（Text2Image，T2I）。现从事多模态（Multi-Model），生成对抗网络（Generative Adversarial Network， GAN）以及小样本（Few-shot Learning）的研究。GAN以及Sampling Methods的论文放在了./GAN and Sampling Methods/README.md中。
正常情况下每周对论文会有所更新。
-
卷积的概念以及基础，主要是前两个章节，有兴趣的可以多看看。
-
吴恩达机器学习，主要是第9-11章节梯度回传部分，有兴趣的可以考虑都看完。机器学习完整版的学习看吴恩达和李宏毅的均可以。
-
Pytorch一小时入门，这是Pytorch的简单入门，一些基础操作，很快就可以看完了。
-
ResNet，ResNet是CNN中的经典框架，
ResNet_CIFAR10.py是一个简易的图像分类代码。
CUDA_VISIBLE_DEVICES=0 python ResNet_CIFAR10.py
-
PyTorch example，这是PyTorch的官方模板平台，学习PyTorch高端操作最好的样例。
-
如何读论文——论文精读，这是李沐大神在B站分享的项目，持续跟进可以很好规范自己的科研习惯。以及李沐大神教你学AI。
-
李宏毅老师关于GAN的介绍，B站视频链接
-
国内AI公众号两大“顶刊”：机器之心、量子位。平时无聊可以刷刷，增长见闻。
-
刘建平Pinard的博客配套代码
-
《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（持续更新中 ...）📘 在线电子书
-
顶刊：TPAMI(CCF A)， TIP(CCF A)， TMM(CCF B)
-
顶会：NeurIPS， CVPR， ICCV， ECCV， ICML， ICLR， AAAI， ACM MM， IJCAI， KDD， SIGIR， 其中KDD与SIGIR是数据挖掘信息检索的顶会
-
NeurIPS Proceedings包含了NIPS历年的paper。
-
Computer Vision Foundation(CVF) Open Access包含了CVF几个顶会的所有论文，ICCV，CVPR，WACV
-
AMiner是个好东西，收集了各个顶会的论文并根据主题进行分类整理，十分方便。有CVPR2021，NIPS2021，ICCV2021，IJCAI2021，SIGIR2021，KDD2021，ICML2021，ICLR2021等。想要以往的论文只需把网页中的
2021改为Year即可。
| Year | Title | Model | Key Notes | Publication | Paper | Code | Have Read?(Y/N) |
|---|---|---|---|---|---|---|---|
| 2021 | ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement | ReStyle | GAN inversion | ICCV |
Code | Y | |
| 2021 | An image is worth 16x16 words: Transformers for image recognition at scale | Transformer | ViT | ICLR |
N | ||
| 2019 | Implicit Semantic Data Augmentation for Deep Networks | ISDA | NIPS |
Code | Y | ||
| 2021 | Regularizing Deep Networks with Semantic Data Augmentation | ISDA | TPAMI |
Code | Y | ||
| 2016 | Deep Residual Learning for Image Recognition | ResNet | ResBlock | CVPR |
Y | ||
| 2016 | Identity Mappings in Deep Residual Networks | arXiv |
Code | Y | |||
| 2020 | PointRend: Image Segmentation as Rendering | PointRend | Segmentation | CVPR |
Code | N | |
| 2018 | The Perception-Distortion Tradeoff | CVPR |
Y | ||||
| 2017 | Feedback Networks | Feedback | CVPR |
Code | Y | ||
| 2018 | Feedback Convolutional Neural Network for Visual Localization and Segmentation | FBCNN | TPAMI |
Code | Y | ||
| 2020 | Batch Normalization Biases Deep Residual Networks Towards Shallow Paths | NIPS |
Y | ||||
| 2020 | Designing Network Design Spaces | CVPR |
Code | Y | |||
| 2017 | Wasserstein GAN | WGAN | GAN | arXiv |
Code | Y | |
| 2017 | Improved Training of Wasserstein GANs | WGAN-GP | GAN | arXiv |
Code | Y | |
| 2018 | Spectral Normalization for Generative Adversarial Networks | SPNorm | GAN | ICLR |
Y | ||
| 2017 | Densely Connected Convolutional Networks | DenseNet | CVPR |
Code | Y | ||
| 2021 | Hybrid-attention guided network with multiple resolution features for person re-identification | ReID | INS |
N | |||
| 2020 | ActBERT: Learning Global-Local Video-Text Representations | ActBERT | arXiv |
Y | |||
| 2020 | Unbiased Scene Graph Generation from Biased Training | SGG | Scene Graph | CVPR |
Code | Y | |
| 2019 | Adversarial Feedback Loop | AFL | GAN | ICCV |
Code | Y | |
| 2020 | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | ECCV |
Code | Y | |||
| 2021 | Rethinking “Batch” in BatchNorm | arXiv |
Y | ||||
| 2018 | Unsupervised Feature Learning via Non-Parametric Instance Discrimination | CVPR |
Code | Y |
| Year | Title | Model | Key Notes | Publication | Paper | Code | Have Read?(Y/N) |
|---|---|---|---|---|---|---|---|
| 2019 | Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis | MSGANs | T2I | CVPR |
Code | Y |
| Year | Title | Model | Key Notes | Publication | Paper | Code | Have Read?(Y/N) |
|---|---|---|---|---|---|---|---|
| 2021 | Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration | GCN | NIPS |
N | |||
| 2019 | Can GCNs Go as Deep as CNNs? | DeepGCN | Point cloud segmentation | ICCV |
Code | Y | |
| 2020 | Feedback Graph Convolutional Network for Skeleton-based Action Recognition | GCN， FB | CVPR |
Y | |||
| 2020 | PairNorm: Tackling Oversmoothing in GNNs | PairNorm | GCN | ICLR |
Code | Y | |
| 2018 | Residual Gated Graph ConvNets | GCN | ICLR |
Code | Y | ||
| 2019 | On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective | GCN | CoRR |
N | |||
| 2020 | Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View | MADGAP | GCN | AAAI |
Code | Y | |
| 2017 | Inductive Representation Learning on Large Graphs | GraphSAGE | GCN | NIPS |
Code | Y | |
| 2018 | Graph Attention Networks | GAT | GCN | ICLR |
Code | Y | |
| 2020 | Benchmarking Graph Neural Networks | GCN | TNNLS |
Code | Y | ||
| 2019 | DropEdge: Towards Deep Graph Convolutional Networks on Node Classification | DropEdge | GCN | ICLR |
Code | Y | |
| 2020 | When Does Self-Supervision Help Graph Convolutional Networks? | GCN | ICML |
Code | Y | ||
| 2019 | Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks | Cluster-GCN | GCN | KDD |
Code | Y | |
| 2020 | Simple and Deep Graph Convolutional Networks | GCNII | GCN | ICML |
Code | Y | |
| 2021 | Isometric Transformation Invariant and Equivariant Graph Convolutional Networks | IsoGCN | GCN | ICLR |
Code | N | |
| 2019 | Attention Models in Graphs: A Survey | GCN | KDD |
N | |||
| 2019 | Graph Convolutional Networks for Temporal Action Localization | PGCN | GCN | ICCV |
Code | N | |
| 2018 | Attention-based Graph Neural Network for Semi-supervised Learning | AGNN | GCN | ICLR |
Y | ||
| 2019 | Understanding Attention and Generalization in Graph Neural Networks | GCN | arXiv |
Code | Y | ||
| 2021 | Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification | GAT | ICLR |
N | |||
| 2021 | Non-Local Graph Neural Networks | NLGCN | GCN | ICLR |
N | ||
| 2021 | When Do GNNs Work: Understanding and Improving Neighborhood Aggregation | GCN | IJCAI |
Y | |||
| 2019 | SPAGAN: Shortest Path Graph Attention Network | SPAGAN | GCN | IJCAI |
Code | Y | |
| 2020 | LFGCN: Levitating over Graphs with Levy Flights | LFGCN | GCN | ICDM |
N | ||
| 2019 | Graph Representation Learning via Hard and Channel-Wise Attention Networks | GCN | KDD |
Y | |||
| 2021 | MULTI-HOP ATTENTION GRAPH NEURAL NETWORKS | MAGNA | GCN | ICLR |
Y | ||
| 2020 | MGAT: Multimodal Graph Attention Network for Recommendation | MGAT | IPM |
Y | |||
| 2018 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | GCN | AAAI |
N | |||
| 2019 | Simplifying Graph Convolutional Networks | SGC | GCN | ICML |
Code | Y | |
| 2021 | Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method | GCN | SIGIR |
Y | |||
| 2017 | SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS | GCN | GCN | ICLR |
Code | Y | |
| 2020 | Open Graph Benchmark: Datasets for Machine Learning on Graphs | OGB | GCN | arXiv |
Code | Y | |
| 2021 | Zero-shot Synthesis with Group-Supervised Learning | GCN | ICLR |
Y |
| Year | Title | Model | Key Notes | Publication | Paper | Code | Have Read?(Y/N) |
|---|---|---|---|---|---|---|---|
| 2021 | Distributed feedback network for single-image deraining | DFN | Derain | INS |
Code | Y | |
| 2019 | EDVR: Video Restoration with Enhanced Deformable Convolutional Networks | EDVR | SR | CVPR |
Code | Y | |
| 2018 | ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks | ESRGAN | SR | ECCV |
Code | Y | |
| 2020 | Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence | SLDNet | Derain | CVPR |
Code | Y | |
| 2020 | Single Image Deraining Using Bilateral Recurrent Network | BRN | Derain | TIP |
Code | Y | |
| 2020 | Multi-Scale Progressive Fusion Network for Single Image Deraining | MSPFN | Derain | CVPR |
Code | Y | |
| 2018 | Residual Dense Network for Image Super-Resolution | RDB | SR | CVPR |
Code | Y | |
| 2019 | Second-order Attention Network for Single Image Super-Resolution | SAN | SR | CVPR |
Code | Y | |
| 2019 | Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset | SPANet | Derain | CVPR |
Code | Y | |
| 2012 | Making a ‘Completely Blind’ Image Quality Analyzer | NIQE | SPL |
Code | Y | ||
| 2020 | DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks | DRD-Net | Derain | CVPR |
Code | Y | |
| 2018 | Density-aware Single Image De-raining using a Multi-stream Dense Network | DID-MDN | Derain | CVPR |
Code | Y | |
| 2020 | Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images | Deraining | CVPR |
Code | Y | ||
| 2014 | No-reference image quality assessment based on spatial and spectralentropies | SSEQ | Signal Processing: Image Communication |
Y | |||
| 2009 | Single Image Haze Removal Using Dark Channel Prior | Dehazing | CVPR |
Code | Y | ||
| 2020 | Cross-Scale Internal Graph Neural Network for image super resolution | SR | NIPS |
Code | Y | ||
| 2017 | Enhanced Deep Residual Networks for Single Image Super-Resolution | EDSR | SR | CVPR |
Code | Y | |
| 2019 | Gated Multiple Feedback Network for Image Super-Resolution | GMFN | SR | BMVC |
Code | Y | |
| 2019 | Image Super-Resolution by Neural Texture Transfer | SR | CVPR |
Code | Y | ||
| 2019 | Progressive Image Deraining Networks: A Better and Simpler Baseline | PReNet | Derain | CVPR |
Code | Y | |
| 2019 | Feedback Network for Image Super-Resolution | SRFBN | Derain | CVPR |
Code | Y | |
| 2019 | Semi-supervised Transfer Learning for Image Rain Removal | SSIR | Derain | CVPR |
Code | Y | |
| 2020 | Confidence Measure Guided Single Image De-raining | Derain | TIP |
N | |||
| 2020 | Rain O'er Me: Synthesizing real rain to derain with data distillation | Deraining | TIP |
N |