一位博士生在学习ML相关论文时，对论文进行了注释和简短摘要。论文和笔记都放在了GitHub上，方便对照。

以下：

Self-Supervised Learning

论文标题：Selfie: Self-supervised Pretraining for Image Embedding (2019)
论文链接：
https://arxiv.org/abs/1906.02940
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/76_selfie_pretraining_for_img_embeddings.pdf

论文标题：Self-Supervised Representation Learning by Rotation Feature Decoupling (2019)
论文链接：
https://github.com/philiptheother/FeatureDecoupling
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/73_SSL_by_rotation_decoupling.pdf

论文标题：Revisiting Self-Supervised Visual Representation Learning (2019)
论文链接：
https://arxiv.org/abs/1901.09005
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/72_revisiting_SSL.pdf

论文标题：AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data (2019)
论文链接：
https://arxiv.org/abs/1901.04596
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/74_AFT_vs_AED.pdf

论文标题：Boosting Self-Supervised Learning via Knowledge Transfer (2018)
论文链接：
https://arxiv.org/abs/1805.00385
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/67_boosting_self_super_via_trsf_learning.pdf

论文标题：Self-Supervised Feature Learning by Learning to Spot Artifacts (2018)
论文链接：
https://arxiv.org/abs/1806.05024
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/69_SSL_by_learn_to_spot_artifacts.pdf

论文标题：Unsupervised Representation Learning by Predicting Image Rotations (2018)
论文链接：
https://arxiv.org/abs/1803.07728
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/68_unsup_img_rep_learn_by_rot_predic.pdf

论文标题：Cross Pixel Optical-Flow Similarity for Self-Supervised Learning (2018)
论文链接：
https://arxiv.org/abs/1807.05636
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/75_cross_pixel_optical_flow.pdf

论文标题：Multi-task Self-Supervised Visual Learning (2017)
论文链接：
https://arxiv.org/abs/1708.07860
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/64_multi_task_self_supervised.pdf

论文标题：Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (2017)
论文链接：
https://arxiv.org/abs/1611.09842
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/65_split_brain_autoencoders.pdf

论文标题：Colorization as a Proxy Task for Visual Understanding (2017)
论文链接：
https://arxiv.org/abs/1703.04044
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/66_colorization_as_a_proxy_for_viz_under.pdf

论文标题：Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (2017)
论文链接：
https://arxiv.org/abs/1603.09246
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/63_solving_jigsaw_puzzles.pdf

论文标题：Unsupervised Visual Representation Learning by Context Prediction (2016)
论文链接：
https://arxiv.org/abs/1505.05192
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/62_unsupervised_learning_with_context_prediction.pdf

论文标题：Colorful image colorization (2016)
论文链接：
https://richzhang.github.io/colorization/
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/59_colorful_colorization.pdf

论文标题：Learning visual groups from co-occurrences in space and time (2015)
论文链接：
https://arxiv.org/abs/1511.06811
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/61_visual_groups_from_co_occurrences.pdf

论文标题：Discriminative unsupervised feature learning with exemplar convolutional neural networks (2015)
论文链接：
https://arxiv.org/abs/1406.6909
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/60_exemplar_CNNs.pdf


Semi-Supervised Learning

论文标题：Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning (2019)
论文链接：
https://arxiv.org/abs/1909.01804
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/79_dual_student.pdf

论文标题：S4L: Self-Supervised Semi-Supervised Learning (2019)
论文链接：
https://arxiv.org/abs/1905.03670
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/83_S4L.pdf

论文标题：Semi-Supervised Learning by Augmented Distribution Alignment (2019)
论文链接：
https://arxiv.org/abs/1905.08171
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/80_SSL_aug_dist_align.pdf

论文标题：MixMatch: A Holistic Approach toSemi-Supervised Learning (2019)
论文链接：
https://arxiv.org/abs/1905.02249
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/45_mixmatch.pdf

论文标题：Unsupervised Data Augmentation (2019)
论文链接：
https://arxiv.org/abs/1904.12848
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/39_unsupervised_data_aug.pdf

论文标题：Interpolation Consistency Training forSemi-Supervised Learning (2019)
论文链接：
https://arxiv.org/abs/1903.03825
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/44_interpolation_consistency_tranining.pdf

论文标题：Deep Co-Training for Semi-Supervised Image Recognition (2018)
论文链接：
https://arxiv.org/abs/1803.05984
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/46_deep_co_training_img_rec.pdf

论文标题：Unifying semi-supervised and robust learning by mixup (2019)
论文链接：
https://openreview.net/forum?id=r1gp1jRN_4
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/42_mixmixup.pdf

论文标题：Realistic Evaluation of Deep Semi-Supervised Learning Algorithms (2018)
论文链接：
https://arxiv.org/abs/1804.09170
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/37_realistic_eval_of_deep_ss.pdf

论文标题：Semi-Supervised Sequence Modeling with Cross-View Training (2018)
论文链接：
https://arxiv.org/abs/1809.08370
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/38_cross_view_semi_supervised.pdf

论文标题：Virtual Adversarial Training:A Regularization Method for Supervised andSemi-Supervised Learning (2017)
论文链接：
https://arxiv.org/abs/1704.03976
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/40_virtual_adversarial_training.pdf

论文标题：Mean teachers are better role models (2017)
论文链接：
https://arxiv.org/abs/1703.01780
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/56_mean_teachers.pdf

论文标题：Temporal Ensembling for Semi-Supervised Learning (2017)
论文链接：
https://arxiv.org/abs/1610.02242
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/55_temporal-ensambling.pdf

论文标题：Semi-Supervised Learning with Ladder Networks (2015)
论文链接：
https://arxiv.org/abs/1507.02672
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/33_ladder_nets.pdf


Unsupervised Learning

论文标题：Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2019)
论文链接：
https://arxiv.org/abs/1807.06653
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/78_IIC.pdf

论文标题：Deep Clustering for Unsupervised Learning of Visual Feature (2018)
论文链接：
https://arxiv.org/abs/1807.05520
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/70_deep_clustering_for_un_visual_features.pdf


Semantic Segmentation

论文标题：DeepLabv3+: Encoder-Decoder with Atrous Separable Convolution (2018)
论文链接：
https://arxiv.org/abs/1802.02611
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/26_deeplabv3+.pdf

论文标题：Large Kernel Matter, Improve Semantic Segmentation by Global Convolutional Network (2017)
论文链接：
https://arxiv.org/abs/1703.02719
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/28_large_kernel_maters.pdf

论文标题：Understanding Convolution for Semantic Segmentation (2018)
论文链接：
https://arxiv.org/abs/1702.08502
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/29_understanding_conv_for_sem_seg.pdf

论文标题：Rethinking Atrous Convolution for Semantic Image Segmentation (2017)
论文链接：
https://arxiv.org/abs/1706.05587
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/25_deeplab_v3.pdf

论文标题：RefineNet: Multi-path refinement networks for high-resolution semantic segmentation (2017)
论文链接：
https://arxiv.org/abs/1611.06612
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/31_refinenet.pdf

论文标题：Pyramid Scene Parsing Network (2017)
论文链接：
http://jiaya.me/papers/PSPNet_cvpr17.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/22_pspnet.pdf

论文标题：SegNet: A Deep ConvolutionalEncoder-Decoder Architecture for ImageSegmentation (2016)
论文链接：
https://arxiv.org/pdf/1511.00561
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/21_segnet.pdf

论文标题：ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation (2016)
论文链接：
https://arxiv.org/abs/1606.02147
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/27_enet.pdf

论文标题：Attention to Scale: Scale-aware Semantic Image Segmentation (2016)
论文链接：
https://arxiv.org/abs/1511.03339
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/30_atttention_to_scale.pdf

论文标题：Deeplab: semantic image segmentation with DCNN, atrous convs and CRFs (2016)
论文链接：
https://arxiv.org/abs/1606.00915
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/23_deeplab_v2.pdf

论文标题：U-Net: Convolutional Networks for Biomedical Image Segmentation (2015)
论文链接：
https://arxiv.org/abs/1505.04597
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/20_Unet.pdf

论文标题：Fully Convolutional Networks for Semantic Segmentation (2015)
论文链接：
https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/19_FCN.pdf

论文标题：Hypercolumns for object segmentation and fine-grained localization (2015)
论文链接：
http://home.bharathh.info/pubs/pdfs/BharathCVPR2015.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/24_hypercolumns.pdf


Weakly

论文标题：Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation (2019)
论文链接：
http://arxiv.org/abs/1904.11693
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/54_boxe_driven_weakly_segmentation.pdf

论文标题：FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference (2019)
论文链接：
https://arxiv.org/abs/1902.10421
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/49_ficklenet.pdf

论文标题：Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (2018)
论文链接：
http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/53_deep_seeded_region_growing.pdf

论文标题：Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation (2018)
论文链接：
https://arxiv.org/abs/1803.10464
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/81_affinity_for_ws_segmentation.pdf

论文标题：Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach (2018)
论文链接：
https://arxiv.org/abs/1703.08448
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/51_object_region_manning_for_sem_seg.pdf

论文标题：Revisiting Dilated Convolution: A Simple Approach for Weakly
论文标题：and Semi
论文标题：Supervised Semantic Segmentation (2018)
论文链接：
https://arxiv.org/abs/1805.04574
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/52_dilates_convolution_semi_super_segmentation.pdf

论文标题：Tell Me Where to Look: Guided Attention Inference Network (2018)
论文链接：
https://arxiv.org/abs/1802.10171
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/50_tell_me_where_to_look.pdf

论文标题：Semi Supervised Semantic Segmentation Using Generative Adversarial Network (2017)
论文链接：
https://arxiv.org/abs/1703.09695
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/82_ss_segmentation_gans.pdf

论文标题：Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation (2015)
论文链接：
https://arxiv.org/abs/1506.04924
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/47_decoupled_nn_for_segmentation.pdf

论文标题：Weakly
论文标题：and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation (2015)
论文链接：
https://arxiv.org/abs/1502.02734
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/48_weakly_and_ss_for_segmentation.pdf


Information Retrieval

论文标题：VSE++: Improving Visual-Semantic Embeddings with Hard Negatives (2018)
论文链接：
https://arxiv.org/abs/1707.05612
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/77_vse++.pdf


Visual Explanation & Attention

论文标题：Attention Branch Network: Learning of Attention Mechanism for Visual Explanation (2019)
论文链接：
https://arxiv.org/abs/1812.10025
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/57_attention_branch_netwrok.pdf

论文标题：Attention-based Dropout Layer for Weakly Supervised Object Localization (2019)
论文链接：
http://openaccess.thecvf.com/content_CVPR_2019/papers/Choe_Attention-Based_Dropout_Layer_for_Weakly_Supervised_Object_Localization_CVPR_2019_paper.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/58_attention_based_dropout.pdf

论文标题：Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer (2016)
论文链接：
https://arxiv.org/abs/1612.03928
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/71_attention_transfer.pdf


Graph neural network & Graph embeddings

论文标题：Pixels to Graphs by Associative Embedding (2017)
论文链接：
https://arxiv.org/abs/1706.07365
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/36_pixels_to_graphs.pdf

论文标题：Associative Embedding: End-to-End Learning forJoint Detection and Grouping (2017)
论文链接：
https://arxiv.org/abs/1611.05424
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/35_associative_emb.pdf

论文标题：Interaction Networks for Learning about Objects , Relations and Physics (2016)
论文链接：
https://arxiv.org/abs/1612.00222
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/18_interaction_nets.pdf

论文标题：DeepWalk: Online Learning of Social Representation (2014)
论文链接：
http://www.perozzi.net/publications/14_kdd_deepwalk.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/deep_walk.pdf

论文标题：The graph neural network model (2009)
论文链接：
https://persagen.com/files/misc/scarselli2009graph.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/graph_neural_nets.pdf


Regularization

论文标题：Manifold Mixup: Better Representations by Interpolating Hidden States (2018)
论文链接：
https://arxiv.org/abs/1806.05236
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/43_manifold_mixup.pdf


Deep learning Methods & Models

论文标题：AutoAugment (2018)
论文链接：
https://arxiv.org/abs/1805.09501
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/41_autoaugment.pdf

论文标题：Stacked Hourgloass (2017)
论文链接：
http://ismir2018.ircam.fr/doc/pdfs/138_Paper.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/34_stacked_hourglass.pdf


Document analysis and segmentation

论文标题：dhSegment: A generic deep-learning approach for document segmentation (2018)
论文链接：
https://arxiv.org/abs/1804.10371
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/dhSegement.pdf

论文标题：Learning to extract semantic structure from documents using multimodal fully convolutional neural networks (2017)
论文链接：
https://arxiv.org/abs/1706.02337
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/learning_to_extract.pdf

论文标题：Page Segmentation for Historical Handwritten Document Images Using Conditional Random Fields (2016)
论文链接：
https://www.researchgate.net/publication/312486501_Page_Segmentation_for_Historical_Handwritten_Document_Images_Using_Conditional_Random_Fields
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/seg_with_CRFs.pdf

论文标题：ICDAR 2015 competition on text line detection in historical documents (2015)
论文链接：
http://ieeexplore.ieee.org/abstract/document/7333945/
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/ICDAR2015.pdf

论文标题：Handwritten text line segmentation using Fully Convolutional Network (2017)
论文链接：
https://ieeexplore.ieee.org/document/8270267/
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/handwritten_text_seg_FCN.pdf

论文标题：Deep Neural Networks for Large Vocabulary Handwritten Text Recognition (2015)
论文链接：
https://tel.archives-ouvertes.fr/tel-01249405/document
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/andwriten_text_recognition.pdf

论文标题：Page Segmentation of Historical Document Images with Convolutional Autoencoders (2015)
论文链接：
https://ieeexplore.ieee.org/abstract/document/7333914/
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/segmentation_with_CAE.pdf

论文标题：A typed and handwritten text block segmentation system for heterogeneous and complex documents (2012)
论文链接：
https://www.researchgate.net/publication/275518176_A_Typed_and_Handwritten_Text_Block_Segmentation_System_for_Heterogeneous_and_Complex_Documents
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/a_typed_block_seg.pdf

论文标题：Document layout analysis, Classical approaches (1992:2001)
论文链接：
https://pdfs.semanticscholar.org/5392/90b571b918da959fabaae7f605bb07850518.pdf
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/old_classical_approaches.pdf

论文标题：Page Segmentation for Historical Document Images Based on Superpixel Classification with Unsupervised Feature Learning (2016)
论文链接：
https://ieeexplore.ieee.org/document/7490134
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/seg_with_superpixels.pdf

论文标题：Paragraph text segmentation into lines with Recurrent Neural Networks (2015)
论文链接：
http://ieeexplore.ieee.org/abstract/document/7333803/
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/textlines_srg_with_RNNs.pdf

论文标题：A comprehensive survey of mostly textual document segmentation algorithms since 2008 (2017 )
论文链接：
https://hal.archives-ouvertes.fr/hal-01388088/document
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/survey_doc_segmentation.pdf

论文标题：Convolutional Neural Networks for Page Segmentation of Historical Document Images (2017)
论文链接：
https://arxiv.org/abs/1704.01474
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/CNNs_chen.pdf

论文标题：ICDAR2009 Page Segmentation Competition (2009)
论文链接：
https://ieeexplore.ieee.org/document/5277763
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/ICDAR2009.pdf

论文标题：Amethod for combining complementary techniques for document image segmentation (2009)
论文链接：
https://www.researchgate.net/publication/220600948_A_method_for_combining_complementary_techniques_for_document_image_segmentation
笔记链接：
https://github.com/yassouali/ML_paper_notes/blob/master/notes/a_method_for_combining_complementary_techniques.pdf

完整列表：
https://github.com/yassouali/ML_paper_notes