https://github.com/swall0w/papers
This is a repository for summarizing papers especially related to machine learning.
https://github.com/swall0w/papers
deep-learning machine-learning papers summary
Last synced: 28 days ago
JSON representation
This is a repository for summarizing papers especially related to machine learning.
- Host: GitHub
- URL: https://github.com/swall0w/papers
- Owner: Swall0w
- Created: 2017-09-26T08:00:28.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-10-13T08:55:06.000Z (over 5 years ago)
- Last Synced: 2025-02-04T23:13:36.997Z (3 months ago)
- Topics: deep-learning, machine-learning, papers, summary
- Homepage:
- Size: 43.5 MB
- Stars: 64
- Watchers: 6
- Forks: 7
- Open Issues: 627
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Papers
Memos for papers, which are related to ML, CV and NLP.
# CV
## Recognition
* [Wide Residual Networks](./papers/000010.Wide_Residual_Networks.md)
* [Densely Connected Convolutional Networks](./papers/000015.Densely_Connected_Convolutional_Networks.md)
* [Deep Pyramidal Residual Networks with Separated Stochastic Depth](./papers/000023.Deep_Pyramidal_Residual_Networks_with_Separated_Stochastic_Depth.md)
* [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](./papers/000029.SqueezeNet_AlexNet-level_accuracy_with_50x_fewer_parameters_and_0.5MB_model_size.md)
* [Dual Path Networks](./papers/000030.Dual_Path_Networks.md)
* [CondenseNet: An Efficient DenseNet using Learned Group Convolutions](./papers/000038.CondenseNet_An_Efficient_DenseNet_using_Learned_Group_Convolutions.md)
* [Recurrent Models of Visual Attention](./papers/000041.Recurrent_Models_of_Visual_Attention.md)
## Detection (Including Instance Segmentation)
* [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](./papers/000004.Faster_R-CNN_Towards_Real-Time_Object_Detection_with_Region_Proposal_Networks.md)
* [SSD: Single Shot MultiBox Detector](./papers/000007.SSD_Single_Shot_MultiBox_Detector.md)
* [Feature Pyramid Networks for Object Detection](./papers/000008.Feature_Pyramid_Networks_for_Object_Detection.md)
* [DSSD : Deconvolutional Single Shot Detector](./papers/000009.DSSD_Deconvolutional_Single_Shot_Detector.md)
* [Speed/accuracy trade-offs for modern convolutional object detectors](./papers/000018.Speed_accuracy_trade-offs_for_modern_convolutional_object_detectors.md)
* [Focal Loss for Dense Object Detection](./papers/000019.Focal_Loss_for_Dense_Object_Detection.md)
* [DetNet: A Backbone network for Object Detection](./papers/000046.DetNet_A_Backbone_network_for_Object_Detection.md)
* [Light-Head R-CNN: In Defense of Two-Stage Object Detector](./papers/000048.Light-Head_R-CNN_In_Defense_of_Two-Stage_Object_Detector.md)
* [Fully Convolutional Instance-aware Semantic Segmentation](./papers/000049.Fully_Convolutional_Instance-aware_Semantic_Segmentation.md)
* [Mask R-CNN](./papers/000051.Mask_R-CNN.md)
* [Fast and accurate object detection in high resolution 4K and 8K video using GPUs](./papers/000056.Fast_and_accurate_object_detection_in_high_resolution_4K_and_8K_video_using_GPUs.md)
* [Revisiting RCNN: On Awakening the Classification Power of Faster RCNN](papers/000062.Revisiting_RCNN.md)
## Pedestrian detection
* [Faster R-CNN with Densenet for scale aware pedestrian detection vis-a-vis head negative suppression](papers/000063_Faster_RCNN_with_densenet.md)
## Semantic Segmentation
* [Fully Convolutional Networks for Semantic Segmentation](./papers/000013.Fully_Convolutional_Networks_for_Semantic_Segmentation.md)
* [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](./papers/000016.SegNet_A_Deep_Convolutional_Encoder-Decoder_Architecture_for_Image_Segmentation.md)
* [U-Net: Convolutional Networks for Biomedical Image Segmentation](./papers/000017.U-Net_Convolutional_Networks_for_Biomedical_Image_Segmentation.md)
## Captioning
* [Self-critical Sequence Training for Image Captioning](./papers/000001.Self-critical_Sequence_Training_for_Image_Captioning.md)
* [Show and Tell: A Neural Image Caption Generator](./papers/000002.Show_and_Tell_A_Neural_Image_Caption_Generator.md)
* [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](./papers/000014.Show_Attend_and_Tell:Neural_Image_Caption_Generation_with_Visual_Attention.md)
* [Deep visual-semantic alignments for generating image descriptions](./papers/000027.Deep_visual-semantic_alignments_for_generating_image_descriptions.md)
## GAN
* [Generative Adversarial Nets](./papers/000006.Generative_Adversarial_Nets.md)
* [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](./papers/000011.Unpaired_Image-to-Image_Translation_using_Cycle-Consistent_Adversarial_Networks.md)
* [Image-to-Image Translation with Conditional Adversarial Networks](./papers/000022.Image_to_Image_Translation_with_Conditional_Adversarial_Networks.md)
* [cGAN-based Manga Colorization Using a Single Training Image](./papers/000026.cGAN-based_Manga_Colorization_Using_a_Single_Training_Image.md)
* [Learning from Simulated and Unsupervised Images through Adversarial Training](./papers/000040.Learning_from_Simulated_and_Unsupervised_Images_through_Adversarial_Training.md)
## Robust Reading
* [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://github.com/Swall0w/papers/blob/master/papers/000039.TextBoxes%2B%2B_A%20Single-Shot_Oriented_Scene_Text_Detector.md)
* [Synthetic data generation for Indic handwritten text recognition](./papers/000044.Synthetic_data_generation_for_Indic_handwritten_text_recognition.md)
* [Reading Scene Text with Attention Convolutional Sequence Modeling](https://github.com/Swall0w/papers/blob/master/papers/000047.%20Reading_Scene_Text_with_Attention_Convolutional_Sequence_Modeling.md)
## Visualization
* [SmoothGrad: removing noise by adding noise](./papers/000012.SmoothGrad_removing_noise_by_adding_noise.md)
## Video
### Tracking
* [Improving Online Multiple Object tracking with Deep Metric Learning](./papers/000057.Improving_Online_Multiple_Object_tracking_with_Deep_Metric_Learning.md)
* [SIMPLE ONLINE AND REALTIME TRACKING](./papers/000058.SIMPLE_ONLINE_AND_REALTIME_TRACKING.md)
### Detection
* [Mobile Video Object Detection with Temporally-Aware Feature Maps](./papers/000053.Mobile_Video_Object_with_Temporally-Aware_Feature_Maps.md)
* [Towards High Performance Video Object Detection for Mobiles](./papers/000052.Towards_High_Performance_Video_Object_Detection_for_Mobiles.md)
### Else
* [Multiple Frames Matching for Object Discovery in Video](./papers/000003.Multiple_Frame_Matching_for_Object_Discovery_in_Video.md)
* [Unsupervised Learning of Video Representations using LSTMs](./papers/000032.Unsupervised_Learning_of_Video_Representations_using_LSTMs.md)
* [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](./papers/000055.Can_Spatiotemporal_3D_CNNs_Retrace_the_History_of_2D_CNNs_and_ImageNet.md)
* [DeepMark: One-Shot Clothing Detection](papers/000061_DeepMark_One_shot_Clothing_Detection.md)
# 3D
* [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](./papers/000036.PointNet++_Deep_Hierarchical_Feature_Learning_on_Point_Sets_in_a_Metric_Space.md)
## Else
* [FlowNet: Learning Optical Flow with Convolutional Networks](./papers/000020.FlowNet_Learning_Optical_Flow_with_Convolutional_Networks.md)
* [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](./papers/000028.FlowNet2.0_Evolution_of_Optical_Flow_Estimation_with_Deep_Networks.md)
* [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](./papers/000031.Revisiting_Unreasonable_Effectiveness_of_Data_in_Deep_Learning_Era.md)
* [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://github.com/Swall0w/papers/blob/master/papers/000037.Learning%20to_Compose_Domain-Specific_Transformations_for_Data_Augmentation.md)
* [Spatial Transformer Networks](./papers/000043.Spatial_Transformer_Networks.md)
# NLP
## NMT
* [Effective Approaches to Attention-based Neural Machine Translation](./papers/000021.Effective_Approaches_to_Attention-based_Neural_Machine_Translation.md)
* [Neural Machine Translation by Jointly Learning to Align and Translate](./papers/000025.Neural_Machine_Translation_by_Jointly_Learning_to_Align_and_Translate.md)
* [Sequence to Sequence Learning with Neural Networks](./papers/000033.Sequence_to_Sequence_Learning_with_Neural_Networks.md)
* [Attention Is All You Need](./papers/000054.Attention_Is_All_You_Need.md)
# ML
* [Positive-Unlabeled Learning with Non-Negative Risk Estimator](./papers/000035.Positive-Unlabeled_Learning_with_Non-Negative_Risk_Estimator.md)
# ELSE
* [Unsupervised Deep Embedding for Clustering Analysis](./papers/000005.Unsupervised_Deep_Embedding_for_Clustering_Analysis.md)
* [Attention-Based Models for Speech Recognition](./papers/000024.Attention-Based_Models_for_Speech_Recognition.md)
* [Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex](./papers/000034.Bridging_the_Gaps_Between_Residual_Learning_Recurrent_Neural_Networks_and_Visual_Cortex.md)
* [What’s your ML Test Score? A rubric for ML production systems](./papers/000042.Whats_your_ML_Test_Score?_A_rubric_for_ML_production_systems.md)
* [Multimodal Emoji Prediction](./papers/000045.Multimodal_Emoji_Prediction.md)
* [Born Again Neural Networks](./papers/000050.Born_Again_Neural_Networks.md)
* [Digital Auditor: A Framework for Matching Duplicate Invoices](papers/000059.Digital_Auditor.md)
* [Pedestrian Detection: A Benchmark](papers/000060_Pedestrian_Detection_benchmark.md)