{"id":13713664,"url":"https://github.com/aleju/papers","last_synced_at":"2025-03-23T08:13:23.782Z","repository":{"id":38360610,"uuid":"52121440","full_name":"aleju/papers","owner":"aleju","description":"Summaries of machine learning papers","archived":false,"fork":false,"pushed_at":"2020-10-29T17:10:04.000Z","size":40247,"stargazers_count":2502,"open_issues_count":5,"forks_count":441,"subscribers_count":266,"default_branch":"master","last_synced_at":"2025-01-28T14:47:23.685Z","etag":null,"topics":["computer-vision","deep-learning","deep-reinforcement-learning","gan","machine-learning","nlp","paper","summary"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aleju.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-02-19T22:44:27.000Z","updated_at":"2025-01-26T16:49:45.000Z","dependencies_parsed_at":"2022-07-08T10:42:26.673Z","dependency_job_id":null,"html_url":"https://github.com/aleju/papers","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aleju%2Fpapers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aleju%2Fpapers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aleju%2Fpapers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aleju%2Fpapers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aleju","download_url":"https://codeload.github.com/aleju/papers/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245072268,"owners_count":20556353,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","deep-learning","deep-reinforcement-learning","gan","machine-learning","nlp","paper","summary"],"created_at":"2024-08-02T23:01:41.662Z","updated_at":"2025-03-23T08:13:23.756Z","avatar_url":"https://github.com/aleju.png","language":null,"readme":"# About\n\nThis repository contains short summaries of some machine learning papers.\n\n## Added 2018/10/01:\n  * ****`UNSUPERVISED LEARNING`**** ****`ECCV 2018`**** [Deep Clustering for Unsupervised Learning of Visual Features](neural-nets/Deep_Clustering_for_Unsupervised_Learning_of_Visual_Features.md)\n  * ****`OBJECT DETECTION`**** ****`POINT CLOUD`**** ****`SELF-DRIVING CARS`**** ****`ECCV 2018`**** [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](neural-nets/Deep_Continuous_Fusion_for_Multi-Sensor_3D_Object_Detection.md)\n  * ****`AUDIO`**** ****`SOUND SOURCE LOCALIZATION`**** ****`ACTION RECOGNITION`**** ****`SOUND SOURCE SEPARATION`**** ****`SELF-SUPERVISED`**** ****`ECCV 2018`**** [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](neural-nets/Audio-Visual_Scene_Analysis_with_Self-Supervised_Multisensory_Features.md)\n  * ****`UNCERTAINTY`**** ****`ECCV 2018`**** [Towards Realistic Predictors](neural-nets/Towards_Realistic_Predictors.md)\n  * ****`OBJECT DETECTION`**** ****`ECCV 2018`**** [Acquisition of Localization Confidence for Accurate Object Detection](neural-nets/Acquisition_of_Localization_Confidence_for_Accurate_OD.md)\n  * ****`OBJECT DETECTION`**** ****`ECCV 2018`**** [CornerNet: Detecting Objects as Paired Keypoints](neural-nets/CornerNet.md)\n  * ****`NORMALIZATION`**** ****`ECCV 2018`**** [Group Normalization](neural-nets/Group_Normalization.md)\n  * ****`ARCHITECTURES`**** ****`ATTENTION`**** ****`ECCV 2018`**** [Convolutional Networks with Adaptive Inference Graphs](neural-nets/Convolutional_Networks_with_Adaptive_Inference_Graphs.md)\n\n## Added 2018/03/08:\n  * ****`ARCHITECTURES`**** ****`ATTENTION`**** [Spatial Transformer Networks](neural-nets/STN.md) (thanks, [alexobednikov](https://github.com/alexobednikov))\n\n## Added 2018/03/06:\n  * ****`LOSS FUNCTIONS`**** ****`RECOGNITION`**** [Working hard to know your neighbor’s margins: Local descriptor learning loss](neural-nets/HardNet.md) (thanks, [alexobednikov](https://github.com/alexobednikov))\n\n## Added 2017/12/13:\n  * ****`FACE RECOGNITION`**** ****`FACES`**** [Neural Aggregation Network for Video Face Recognition](neural-nets/NAN_for_Video_Face_Recognition.md) (thanks, [alexobednikov](https://github.com/alexobednikov))\n\n## Added 2017/12/03:\n  * [Critical Learning Periods in Deep Neural Networks](neural-nets/Critical_Learning_Periods_in_Deep_Neural_Networks.md)\n  * ****`GAN`**** ****`SELF-DRIVING CARS`**** [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](neural-nets/High_Resolution_Image_Synthesis_with_Conditional_GANs.md)\n  * ****`SELF-DRIVING CARS`**** [Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art](mixed/Computer_Vision_for_Autonomous_Vehicles_Overview.md)\n\n## Added 2017/10/28:\n  * ****`GAN`**** [Progressive Growing of GANs for Improved Quality, Stability, and Variation](neural-nets/Progressive_Growing_of_GANs.md)\n\n## Added 2017/10/24:\n  * ****`SELF-DRIVING CARS`**** [Systematic Testing of Convolutional Neural Networks for Autonomous Driving](neural-nets/Systematic_Testing_of_CNNs_for_Autonomous_Driving.md)\n  * ****`SELF-DRIVING CARS`**** ****`SEGMENTATION`**** [Fast Scene Understanding for Autonomous Driving](neural-nets/Fast_Scene_Understanding_for_Autonomous_Driving.md)\n  * ****`SELF-DRIVING CARS`**** [Arguing Machines: Perception-Control System Redundancy and Edge Case Discovery in Real-World Autonomous Driving](neural-nets/Arguing_Machines.md)\n  * ****`SELF-DRIVING CARS`**** ****`GAN`**** ****`REINFORCEMENT`**** [Virtual to Real Reinforcement Learning for Autonomous Driving](neural-nets/Virtual_to_Real_RL_for_AD.md)\n  * ****`SELF-DRIVING CARS`**** [End to End Learning for Self-Driving Cars](neural-nets/End_to_End_Learning_for_Self-Driving_Cars.md)\n\n## Added 2017/10/21:\n  * [Snapshot Ensembles: Train 1, get M for free](neural-nets/Snapshot_Ensembles.md)\n  * [Image Crowd Counting Using Convolutional Neural Network and Markov Random Field](neural-nets/Image_Crowd_Counting_using_CNN_and_MRF.md)\n  * ****`REINFORCEMENT`**** [Rainbow: Combining Improvements in Deep Reinforcement Learning](neural-nets/Rainbow.md)\n  * ****`REINFORCEMENT`**** [Learning to Navigate in Complex Environments](neural-nets/Learning_to_Navigate_in_Complex_Environments.md)\n  * ****`GAN`**** [Unsupervised Image-to-Image Translation Networks](neural-nets/Unsupervised_Image-to-Image_Translation_Networks.md)\n  * ****`RNN`**** [Dilated Recurrent Neural Networks](neural-nets/Dilated_Recurrent_Neural_Networks.md)\n  * ****`OBJECT DETECTION`**** ****`TRACKING`**** [Detect to Track and Track to Detect](neural-nets/Detect_to_Track_and_Track_to_Detect.md)\n  * ****`ARCHITECTURES`**** [Dilated Residual Networks](neural-nets/Dilated_Residual_Networks.md)\n\n## Added 2017/09/24:\n  * ****`OBJECT DETECTION`**** [Feature Pyramid Networks for Object Detection](neural-nets/Feature_Pyramid_Networks_for_Object_Detection.md)\n  * ****`OBJECT DETECTION`**** [SSD: Single Shot MultiBox Detector](neural-nets/SSD.md)\n  * ****`OBJECT DETECTION`**** ****`EFFICIENT NETWORKS`**** [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](neural-nets/MobileNets.md)\n  * ****`OBJECT DETECTION`**** [Mask R-CNN](neural-nets/Mask_R-CNN.md)\n\n## Added 2017/08/08:\n  * ****`FACES`**** [Multi-view Face Detection Using Deep Convolutional Neural Networks](neural-nets/Multi-view_Face_Detection_Using_Deep_Convolutional_Neural_Networks.md) (aka DDFD) (thanks, [arnaldog12](https://github.com/arnaldog12))\n\n## Added 2017/06/11:\n  * ****`GAN`**** [On the Effects of Batch and Weight Normalization in Generative Adversarial Networks](neural-nets/On_The_Effects_of_BN_and_WN_in_GANs.md)\n  * ****`GAN`**** [BEGAN](neural-nets/BEGAN.md)\n  * ****`GAN`**** [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](neural-nets/StackGAN.md)\n  * ****`ACTIVATION FUNCTIONS`**** [Self-Normalizing Neural Networks](neural-nets/Self-Normalizing_Neural_Networks.md)\n  * ****`GAN`**** [Wasserstein GAN](neural-nets/WGAN.md) (aka WGAN)\n\n## Added 2017/03/15:\n  * ****`OBJECT DETECTION`**** [YOLO9000: Better, Faster, Stronger](neural-nets/YOLO9000.md) (aka YOLOv2)\n  * ****`OBJECT DETECTION`**** [You Only Look Once: Unified, Real-Time Object Detection](neural-nets/YOLO.md) (aka YOLO)\n  * ****`OBJECT DETECTION`**** [PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection](neural-nets/PVANET.md)\n\n## Added 2017/03/14:\n  * ****`OBJECT DETECTION`**** [R-FCN: Object Detection via Region-based Fully Convolutional Networks](neural-nets/R-FCN.md)\n  * ****`OBJECT DETECTION`**** [Faster R-CNN](neural-nets/Faster_R-CNN.md)\n  * ****`OBJECT DETECTION`**** [Fast R-CNN](neural-nets/Fast_R-CNN.md)\n  * ****`OBJECT DETECTION`**** [Rich feature hierarchies for accurate object detection and semantic segmentation](neural-nets/Rich_feature_hierarchies_for_accurate_object_detection_and_semantic_segmentation.md) (aka R-CNN)\n  * ****`PEDESTRIANS`**** [Ten Years of Pedestrian Detection, What Have We Learned?](mixed/Ten_Years_of_Pedestrian_Detection_What_Have_We_Learned.md)\n  * ****`NEURAL STYLE`**** [Instance Normalization: The Missing Ingredient for Fast Stylization](neural-nets/Instance_Normalization_The_Missing_Ingredient_for_Fast_Stylization.md)\n\n## Added 2016/07/29:\n  * ****`HUMAN POSE ESTIMATION`**** [Stacked Hourglass Networks for Human Pose Estimation](neural-nets/Stacked_Hourglass_Networks_for_Human_Pose_Estimation.md)\n  * ****`FACES`**** [DeepFace: Closing the Gap to Human-Level Performance in Face Verification](neural-nets/DeepFace.md)\n  * ****`TRANSLATION`**** [Character-based Neural Machine Translation](neural-nets/Character-based_Neural_Machine_Translation.md)\n\n## Added 2016/07/01:\n  * ****`HUMAN POSE ESTIMATION`**** [Convolutional Pose Machines](neural-nets/Convolutional_Pose_Machines.md)\n  * ****`FACES`**** [HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition](neural-nets/HyperFace.md)\n  * ****`FACES`**** [Face Attribute Prediction Using Off-the-Shelf CNN Features](neural-nets/Face_Attribute_Prediction_Using_Off-the-Shelf_CNN_Features.md)\n  * ****`FACES`**** [CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection](neural-nets/CMS-RCNN.md)\n  * [Conditional Image Generation with PixelCNN Decoders](neural-nets/Conditional_Image_Generation_with_PixelCNN_Decoders.md)\n  * ****`GAN`**** [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](neural-nets/InfoGAN.md)\n  * ****`GAN`**** [Improved Techniques for Training GANs](neural-nets/Improved_Techniques_for_Training_GANs.md)\n  * [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](neural-nets/Synthesizing_the_preferred_inputs_for_neurons_in_neural_networks_via_deep_generator_networks.md)\n\n## Added 2016/06/06:\n  * ****`ARCHITECTURES`**** [FractalNet: Ultra-Deep Neural Networks without Residuals](neural-nets/FractalNet_Ultra-Deep_Networks_without_Residuals.md)\n  * [PlaNet - Photo Geolocation with Convolutional Neural Networks](neural-nets/PlaNet.md)\n  * ****`OPTIMIZERS`**** [Adam: A Method for Stochastic Optimization](neural-nets/Adam.md)\n  * ****`GAN`**** ****`RNN`**** [Generating images with recurrent adversarial networks](neural-nets/Generating_Images_with_Recurrent_Adversarial_Networks.md)\n  * ****`GAN`**** [Adversarially Learned Inference](neural-nets/Adversarially_Learned_Inference.md)\n\n## Added 2016/06/02:\n  * ****`ARCHITECTURES`**** [Resnet in Resnet: Generalizing Residual Architectures](neural-nets/Resnet_in_Resnet.md)\n  * ****`AUTOENCODERS`**** [Rank Ordered Autoencoders](neural-nets/Rank_Ordered_Autoencoders.md)\n  * ****`ARCHITECTURES`**** [Wide Residual Networks](neural-nets/Wide_Residual_Networks.md)\n  * ****`ARCHITECTURES`**** [Identity Mappings in Deep Residual Networks](neural-nets/Identity_Mappings_in_Deep_Residual_Networks.md)\n  * ****`REGULARIZATION`**** [Swapout: Learning an ensemble of deep architectures](neural-nets/Swapout.md)\n  * [Multi-Scale Context Aggregation by Dilated Convolutions](neural-nets/Multi-Scale_Context_Aggregation_by_Dilated_Convolutions.md)\n  * [Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints](neural-nets/Texture_Synthesis_Through_CNNs_and_Spectrum_Constraints.md)\n  * [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](neural-nets/Markovian_GANs.md)\n\n## Added 2016/05/15:\n  * ****`NEURAL STYLE`**** [Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork](neural-nets/Neural_Doodle.md)\n  * [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](neural-nets/Combining_MRFs_and_CNNs_for_Image_Synthesis.md)\n  * ****`SUPERRESOLUTION`**** [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](neural-nets/Accurate_Image_Super-Resolution.md)\n  * ****`HUMAN POSE ESTIMATION`**** [Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation](neural-nets/Joint_Training_of_a_ConvNet_and_a_PGM_for_HPE.md)\n  * ****`REINFORCEMENT`**** [Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation](neural-nets/Hierarchical_Deep_Reinforcement_Learning.md)\n  * ****`COLORIZATION`**** [Let there be Color](neural-nets/Let_there_be_Color.md)\n\n## Added 2016/05/08:\n  * ****`NEURAL STYLE`**** [Artistic Style Transfer for Videos](neural-nets/Artistic_Style_Transfer_for_Videos.md)\n\n## Added 2016/05/03:\n  * ****`REINFORCEMENT`**** [Playing Atari with Deep Reinforcement Learning](neural-nets/Playing_Atari_with_Deep_Reinforcement_Learning.md)\n  * ****`GENERATIVE`**** [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](neural-nets/Attend_Infer_Repeat.md)\n  * ****`ARCHITECTURES`**** ****`EFFICIENT NETWORKS`**** [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \u003c0.5MB model size](neural-nets/SqueezeNet.md)\n  * ****`ACTIVATION FUNCTIONS`**** [Noisy Activation Functions](neural-nets/Noisy_Activation_Functions.md)\n  * ****`OBJECT DETECTION`**** ****`IMAGE TO TEXT`**** [DenseCap: Fully Convolutional Localization Networks for Dense Captioning](neural-nets/DenseCap.md)\n\n## Added 2016/04/01:\n  * ****`REGULARIZATION`**** [Deep Networks with Stochastic Depth](neural-nets/Deep_Networks_with_Stochastic_Depth.md)\n\n## Added 2016/03/31:\n  * ****`GAN`**** [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](neural-nets/Deep_Generative_Image_Models_using_a_Laplacian_Pyramid_of_Adversarial_Networks.md)\n  * ****`GENERATIVE`**** ****`RNN`**** ****`ATTENTION`**** [DRAW A Recurrent Neural Network for Image Generation](neural-nets/DRAW_A_Recurrent_Neural_Network_for_Image_Generation.md)\n  * [Generating Images with Perceptual Similarity Metrics based on Deep Networks](neural-nets/Generating_Images_with_Perceptual_Similarity_Metrics_based_on_Deep_Networks.md)\n  * ****`GENERATIVE`**** [Generative Moment Matching Networks](neural-nets/Generative_Moment_Matching_Networks.md)\n  * ****`GENERATIVE`**** ****`RNN`**** [Pixel Recurrent Neural Networks](neural-nets/Pixel_Recurrent_Neural_Networks.md)\n  * ****`GAN`**** [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](neural-nets/Unsupervised_Representation_Learning_with_Deep_Convolutional_Generative_Adversarial_Networks.md)\n\n## Added 2016/03/??:\n  * ****`NEURAL STYLE`**** [A Neural Algorithm for Artistic Style](neural-nets/A_Neural_Algorithm_for_Artistic_Style.md)\n  * ****`NORMALIZATION`**** ****`REGULARIZATION`**** [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](neural-nets/Batch_Normalization.md)\n  * ****`ARCHITECTURES`**** [Deep Residual Learning for Image Recognition](neural-nets/Deep_Residual_Learning_for_Image_Recognition.md)\n  * ****`ACTIVATION FUNCTIONS`**** [Fast and Accurate Deep Networks Learning By Exponential Linear Units (ELUs)](neural-nets/ELUs.md)\n  * [Fractional Max-Pooling](neural-nets/Fractional_Max_Pooling.md)\n  * ****`GAN`**** [Generative Adversarial Networks](neural-nets/Generative_Adversarial_Networks.md)\n  * ****`ARCHITECTURES`**** [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](neural-nets/Inception_v4.md)\n  * ****`NORMALIZATION`**** [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](neural-nets/Weight_Normalization.md)\n\n","funding_links":[],"categories":["Machine Learning","Others"],"sub_categories":["JavaScript"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faleju%2Fpapers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faleju%2Fpapers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faleju%2Fpapers/lists"}