【Paper Reading】

【Paper Reading】_第1张图片

Levers are simple too, but they can move the world1.


文章目录

  • 1 Categories
    • Classification
    • Compression
    • Object Detection
    • Segmentation
    • Face Classification / Detection
    • Point Detection
    • ReID
    • High Resolution
    • One Shot
    • Noisy Label
  • 2 期刊会议
    • 2.1 期刊
    • 2.2 会议
  • 3 Speech / Course
  • 4 Material


1 Categories

Classification

  • 【NIN】《Network In Network》(arXiv-2013)

  • 【Highway network】《Training Very Deep Networks》(NIPS-2015)

  • 【Inception-v1】《Going Deeper with Convolutions》(CVPR-2015)

  • 【Inception-v2】《Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift》(ICML-2015)

  • 【Inception-v3】《Rethinking the Inception Architecture for Computer Vision》(CVPR-2016)

  • 【WRNs】《Wide Residual Networks》(arXiv-2016)

  • 【RSCM】《RSCM:Region selection and concurrency model for multi-class weather recognition》(TIP-2017)

  • 【Inception-v4、Inception-Resnet-v1、v2】《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning》(AAAI-2017)

  • 【DenseNet】《Densely Connected Convolutional Networks》(CVPR-2017)

  • 【Xception】《Xception: Deep Learning with Depthwise Separable Convolutions》(CVPR-2017)

  • 【ResNext】《Aggregated Residual Transformations for Deep Neural Networks》(CVPR-2017)

  • 【NasNet】《Learning Transferable Architectures for Scalable Image Recognition》(CVPR-2018)

  • 【SENet】《Squeeze-and-Excitation Networks》(CVPR-2018)

  • 【CBAM】《CBAM: Convolutional Block Attention Module》(ECCV-2018)

  • 【Bilinear Pooling】《A Novel DR Classfication Scheme based on Compact Bilinear Pooling CNN and GBDT》(JIH-MSP-2018)

  • 【FD-MobileNet】《FD-MobileNet:Improved MobileNet with a Fast Downsampling Strategy》(ICIP-2018)

  • 【SKNet】《Selective Kernel Networks》(CVPR-2019)

  • 【BoT】《Bag of Tricks for Image Classification with Convolutional Neural Networks》(CVPR-2019)

  • 【EfficientNet】《EfficientNet:Rethinking Model Scaling for Convolutional Neural Networks》(ICML-2019)

Compression

  • 【Distilling】《Distilling the Knowledge in a Neural Network》(arXiv-2015, In NIPS Deep Learning Workshop, 2014)

  • 【Comprssion】《Deep Compression:Compressing Deep Neural Networks with Pruning,Trained Quantization and Huffman Coding》(ICLR-2016 Best Paper)

  • 【Distilling】《Learning Efficient Object Detection Models with Knowledge Distillation》(NIPS-2017)

  • 【Mimic】《Mimicking Very Efficient Network for Object Detection》(CVPR-2017)

  • 【Very Tiny】《Quantization Mimic: Towards Very Tiny CNN for Object Detection》(ECCV-2018)

  • 【MobileNet】《MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications》(CVPR-2017)

  • 【SqueezeNet】《SqueezeNet:AlexNet-Level accuracy with 50× fewer parameters and <0.5MB model size》(ICLR-2017)

  • 【ShuffleNet】《ShuffleNet:An Extremely Efficient Convolutional Neural Network for Mobile Devices》(CVPR-2018)

  • 【MobileNet V2】《MobileNetV2:Inverted Residuals and Linear Bottlenecks》(CVPR-2018)

  • 【ShuffleNet V2】《ShuffleNet V2:Practical Guidelines for Efficient CNN Architecture Design》(ECCV-2018)

  • 【MnasNet】《MnasNet:Platform-Aware Neural Architecture Search for Mobile》(CVPR-2019)

  • 【MobileNet V3】《Searching for MobileNetV3》(ICCV-2019)

Object Detection

  • 【OverFeat】《OverFeat:Integrated Recognition, Localization and Detection using Convolutional Networks》(ICLR-2014)

  • 【RCNN】《Rich feature hierarchies for accurate object detection and semantic segmentation 》(CVPR-2014)

  • 【SPP-net】《Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition》(ECCV-2014)

  • 【Fast RCNN】《Fast-RCNN》(ICCV-2015)

  • 【Faster RCNN】《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》(NIPS-2015)

  • 【MS-FRCNN】《Multiple Scale Faster-RCNN Approach to Driver’s Cell-phone Usage and Hands on Steering Wheel Detection》(CVPR-2016)

  • 【OHEM】《Training Region-based Object Detectors with Online Hard Example Mining》(CVPR-2016)

  • 【SSD】《SSD:Single Shot MultiBox Detector》(ECCV-2016)

  • 【YOLOv1】《You Only Look Once: Unified, Real-Time Object Detection》 (CVPR-2016)

  • 【R-FCN】《R-FCN: Object Detection via Region-based Fully Convolutional Networks》(NIPS-2016)

  • 【PVANet】《PVANET:Deep but Lightweight Neural Networks for Real-time Object Detection》(arXiv-2016)

  • 【Light-Head RCNN】《Light-Head R-CNN: In Defense of Two-Stage Object Detector》(arXiv-2017)

  • 【FPN】《Feature Pyramid Networks for Object Detection》(CVPR-2017)

  • 【YOLOv2】《YOLO9000:Better, Faster, Stronger》(CVPR-2017)

  • 【Mask RCNN】《Mask R-CNN》(ICCV-2017)

  • 【Focal Loss】《Focal Loss for Dense Object Detection》(ICCV-2017)

  • 【DetNet】《DetNet:A Backbone network for Object Detection》(arXiv-2018)

  • 【YOLOv3】《YOLOv3:An Incremental Improvement》(arXiv-2018)

  • 【USE】《An End-to-End System for Automatic Urinary Particle Recognition
    with Convolutional Neural Network》(JMOS-2018)

  • 【USE】《Object detection based on deep learning for urine sediment examination》(Biocybernetics & Biomedical Engineering, 2018)

  • 【R-FCN-3000】《R-FCN-3000 at 30fps: Decoupling Detection and Classification》(CVPR-2018)

  • 【Cascade R-CNN】《Cascade R-CNN: Delving into High Quality Object Detection》(CVPR-2018)

  • 【NL】《Non-local Neural Networks》(CVPR-2018)

  • 【CornerNet】《CornerNet: Detecting Objects as Paired Keypoints》(ECCV-2018)

  • 【Feature Pyramid】《Deep Feature Pyramid Reconfiguration for Object Detection》(ECCV-2018)

  • 【CenterNet】《Objects as Points》(arXiv-2019)

  • 【MoCo】《Momentum Contrast for Unsupervised Visual Representation Learning》(arXiv-2019)

  • 【TridentNet】《Scale-Aware Trident Networks for Object Detection》(ICCV-2019)

  • 【Up-Sampling】《CARAFE:Content-Aware ReAssembly of FEatures》(ICCV-2019)

  • 【ThunderNet】《ThunderNet: Towards Real-time Generic Object Detection on Mobile Devices》(ICCV-2019)

  • 【Matrix Nets】《Matrix Nets:A New Deep Architecture for Object Detection》(ICCV-2019 workshops)

  • 【Libra R-CNN】《Libra R-CNN: Towards Balanced Learning for Object Detection》(CVPR-2019)

  • 【GIoU】《Generalized Intersection over Union:A Metric and A Loss for Bounding Box Regression》(CVPR-2019)

  • 【DIoU】《Distance-IoU Loss:Faster and Better Learning for Bounding Box Regression》(AAAI-2020)

  • 【D2Det】《 D2Det:Towards High Quality Object Detection and Instance Segmentation》(CVPR-2020)

  • 【Sparse R-CNN】《Sparse R-CNN:End-to-End Object Detection with Learnable Proposals》(arXiv-2020)

  • 【YOLOv4】《YOLOv4:Optimal Speed and Accuracy of Object Detection》(arXiv-2020)

Segmentation

  • 【U-Net】《U-Net:Convolutional Networks for Biomedical Image Segmentation》(MICCAI-2015)

  • 【FCN】《Fully Convolutional Networks for Semantic Segmentation》(CVPR-215 best paper)

  • 【Dilated Conv】《Multi-Scale Context Aggregation by Dilated Convolutions》(ICLR-2016)

  • 【PANet】《Path Aggregation Network for Instance Segmentation》(CVPR-2018)

  • 【BiSeNet】《BiSeNet:Bilateral Segmentation Network for Real-time Semantic Segmentation》(ECCV-2018)

  • 【EmbedMask】《EmbedMask:Embedding Coupling for One-stage Instance Segmentation》(arXiv-2019)

  • 【CenterMask】《CenterMask:Single Shot Instance segmentation with Point Representation》(CVPR-2020)

  • 【PolyTransform】《PolyTransform:Deep Polygon Transformer for Instance Segmentation》(CVPR-2020)

  • 【Point-Set】《Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation》(ECCV-2020)

  • 【Decouple】《Improving Semantic Segmentation via Decoupled Body and Edge Supervision》(ECCV-2020)

  • 【STDC】《Rethinking BiSeNet For Real-time Semantic Segmentation》(CVPR-2021)

  • 【MagNet】《Progressive Semantic Segmentation》(CVPR-2021)

Face Classification / Detection

  • 【DDFD】《Multi-view Face Detection Using Deep Convolutional Neural Networks》(ICMR-2015)

  • 【IoU Loss】《UnitBox: An Advanced Object Detection Network》(ACM MM-2016)

  • 【FAS】《Face Anti-Spoofing Using Patch and Depth-Based CNNs》(IJCB-2017)

  • 【Face Detection】《Face Detection using Deep Learning: An Improved Faster RCNN Approach》(Neurocomputing-2018)

  • 【GDConv】《MobileFaceNets:Efficient CNNs for Accurate RealTime Face Verification on Mobile Devices》(CCBR-2018)

  • 【CASIA-SURF】《A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing》(CVPR-2019)

  • 【FAS-FRN】《Recognizing Multi-modal Face Spoofing with Face Recognition Networks》(CVPR-2019 workshop)

  • 【FaceBagNet】《FaceBagNet:Bag-of-local-features Model for Multi-modal Face Anti-spoofing》(CVPR-2019 workshop)

  • 【FeatherNets】《FeatherNets:Convolutional Neural Networks as Light as Feather for Face Anti-spoofing》(CVPR-2019 workshop)

Point Detection

  • 【Cascade FPD】《Deep Convolutional Network Cascade for Facial Point Detection》(CVPR-2013)

  • 【DeepPose】《DeepPose:Human Pose Estimation via Deep Neural Networks》(CVPR-2014)

  • 【Stacked Hourglass】《Stacked Hourglass Networks for Human Pose Estimation》(ECCV-2016)

  • 【HPM Block】《Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources》(ICCV-2017)

  • 【PRMs】《Learning Feature Pyramids for Human Pose Estimation》(ICCV-2017)

  • 【Heatmap+offset】《Towards Accurate Multi-person Pose Estimation in the Wild》(CVPR-2017)

  • 【Simple Baselines】《Simple Baselines for Human Pose Estimation and Tracking》(ECCV-2018)

  • 【CPN】《Cascaded Pyramid Network for Multi-Person Pose Estimation》(CVPR-2018)

  • 【Knee Landmark】《KNEEL:Knee Anatomical Landmark Localization Using Hourglass Networks》(ICCVW-2019)

  • 【HRNet】《Deep High-Resolution Representation Learning for Human Pose Estimation》(CVPR-2019)

ReID

  • 【SB-ReID】《Bag of Tricks and A Strong Baseline for Deep Person Re-identification》(CVPR-2019)

High Resolution

  • 【YOLT】《You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery》(CVPR-2018被拒)

  • 【WSI】《Faster R-CNN-Based Glomerular Detection in Multistained Human Whole Slide Images》(MDPI-2018)

One Shot

  • 【One Shot】《Siamese Neural Networks for One-shot Image Recognition》(ICML-2015)

  • 【One Shot】《Matching Networks for One Shot Learning》(NIPS-2016)

Noisy Label

  • 【Noise-Label】《Learning from Noisy Labels with Deep Neural Networks》(arXiv-2014)

  • 【Noise-Label】《Training a Neural Network Based on Unreliable Human Annotation of Medical Images》(ISBI-2018)


2 期刊会议

中国计算机学会推荐国际学术刊物

常见的评审制度有单盲评审(single-blind)双盲评审(double-blind)开放式评审(open review) 等。

  • 单盲评审即评审人员对文章进行匿名评审,评审人员知道文章作者的信息。
  • 双盲评审即评审人和文章作者互相都不知道对方的信息,完全匿名。
  • 开放式评审即所有提交的论文都会公开姓名等信息,并且接受所有同行的评价及提问(open peer review),任何学者都可匿名或实名评价论文。而在公开评审结束后,论文作者也能够对论文进行调整和修改。

以下几小段内容来自 2018年学术顶会:深度学习的江山如此多娇

  我们可以看到这些学术顶会的论文提交数量不断增长,有些增幅甚至超 40%。那么一年过去了,合格的论文评审人员的增幅是否赶得上论文的增幅呢?

  答案显而易见。今年 5 月,本科毕业生成为 NeurIPS 2018 论文同行评审的事情引发争议;7 月份,NeurIPS 2018 论文评审结果出来后,很多人吐槽评审意见不专业。几天后,GAN 之父Ian Goodfellow 发推质疑同行评审机制的作用,他认为同行评审导致 AI 顶会论文质量下降,而主要原因正在于评审人员水平不一。此前发表过「机器学习之怪现状」的 Zachary Lipton 同意 Goodfellow 的看法,认为同行评审机制的退化是机器学习怪现状的原因之一。

  除了 Ian Goodfellow、Zachy Lipton 以外,Geoff Hinton 前不久接受采访时称,现在的评审制度和既定路径不利于创新性想法的提出和传播,junior 论文评审者可能压根无法理解创新性论文。关于此,国内学者也有类似看法,著名自然语言处理专家刘群教授说过:「审稿的时候……通常比较 junior 的审稿人会更严厉一些,发现一些小问题就会倾向于给低分,而 senior 的审稿人反倒宽松一些,如果觉得论文确有可取之处,通常不会太计较一些小问题。」此前,南京大学周志华教授称:「senior 知道论文价值就是那点新火花,有毛病没关系。前沿研究要有长处,系统开发要无短处。」


2.1 期刊

  • PAMI
    《IEEE Transactions on Pattern Analysis and Machine Intelligence》是人工智能、模式识别、图像处理、计算机视觉领域的顶尖国际期刊之一,2016-2017年度影响因子为8.329,属于JCR TOP期刊,是计算机科学与人工智能领域的5个一区刊物之一。该杂志覆盖所有计算机视觉、图像理解、模式分析与识别等传统领域,以及部分机器智能领域,尤其强调模式分析的机器学习的前沿成果。

  • TMI
    《IEEE Transactions on Medical Imaging》 (月刊,医学图像处理顶刊)

  • MIA
    《Medical Image Analysis 》(月刊,医学图像处理顶刊)

2.2 会议

  • AAAI (人工智能顶会,A类/年)
    围绕人工智能的研究与发展,吸引了全球的人工智能精英。

  • CVPR(计算机视觉顶会,A类/年)
    《IEEE Conference on Computer Vision and Pattern Recognition》。这个会上除了视觉的文章,还会有不少模式识别的文章,当然两方面的结合自然也是重点。下面是 14-20 年的 paper list 链接

    https://openaccess.thecvf.com/CVPR2014
    https://openaccess.thecvf.com/CVPR2015
    https://openaccess.thecvf.com/CVPR2016
    https://openaccess.thecvf.com/CVPR2017
    https://openaccess.thecvf.com/CVPR2018
    https://openaccess.thecvf.com/CVPR2019
    https://openaccess.thecvf.com/CVPR2020
    https://openaccess.thecvf.com/CVPR2021

  • ECCV(计算机视觉顶会,B类/两年)
    《Europeon Conference on Computer Vision》,是一个欧洲的会议。虽然名字不是International,但是会议的级别不比前面两个差多少。欧洲人一般比较看中理论,但是从最近一次会议来看,似乎大家也开始注重应用了,oral里面的demo非常之多,演示效果很好,让人赏心悦目、叹为观止。不过欧洲的会有一个不好,就是他们的人通常英语口音很重,有些人甚至不太会说英文,所以开会和交流的时候,稍微有些费劲。

  • ICCV(计算机视觉顶会,A类/两年)
    《International Comference on Computer Vision》,正如很多和他一样的名字的会议一行,这样最朴实的名字的会议,通常也是这方面最nb的会议。ICCV两年一次,与ECCV正好错开。

  • ICLR(深度学习顶会/年)
    《International Conference on Learning Representations》国际学习表征会议,2013 年,深度学习巨头 Yoshua Bengio、Yann LeCun 主持举办了第一届 ICLR 大会。经过几年的发展,在深度学习火热的今天,ICLR 已经成为人工智能领域不可错过的盛会之一。

  • ICML(机器学习顶会,A类/年)
    《International Conference on Machine Learning》国际机器学习大会。ICML如今已发展为由国际机器学习学会(IMLS)主办的年度机器学习国际顶级会议。

  • IJCAI(人工智能国际联合大会,A类/年)
    《International Joint Conference on Artificial Intelligence》国际人工智能联合会议,是人工智能领域的顶级综合会议,原为单数年召开,自2015年起改为每年召开。

  • IPMI(医学图像处理顶会/两年)
    《Information Processing in Medical Imaging 》

  • MICCAI(医学图像处理顶会/年)
    《International Conference on Medical Image Computing and Computer Assisted Intervention 》

  • NIPS(人工智能顶会,A类/年)
    《Conference and Workshop on Neural Information Processing Systems》 神经信息处理系统大会
    是一个关于机器学习和计算神经科学的国际会议。该会议固定在每年的12月举行,由NIPS基金会主办。


3 Speech / Course

  • 【Paper material】
  • 【阅读笔记】
  • 【摘抄】英文
  • 【摘抄】中文(私密)
  • 【Andrew Ng】《Class of 2017 Sloan Fellows presents》
  • 【周志华】新智元 AI World 2018 世界人工智能峰会
  • 【National Treasure】
  • 【Career Exploration and Selection】
  • 【Romance of the Three Kingdoms】
  • 【Weather Classification】reading notes
  • 【Structure Light】reading notes(一)

4 Material

  • AI 自动抠图
  • 十分钟快速理解 DPI 和 PPI,不再傻傻分不清!
  • PASCAL VOC2007 Database Statistics
  • PASCAL VOC2012 Database Statistics
  • 旷视南京研究院魏秀参:细粒度图像分析综述(「R Talk 」是旷视推出的一个深度学习专栏,将通过不定期的推送展示旷视科技的学术分享及阶段性技术成果。「R」是 Research 的缩写,也是旷视研究院的内部代号;而所有的「Talk」都是来自旷视的 Researcher。「R Talk 」旨在通过一场场精彩纷呈的深度学习分享,抛砖引玉,推陈出新,推动中国乃至全球领域深度学习技术的大发展。)
  • 俞刚:我在旷视研究院做检测
  • Receptive Field Calculator
  • MS COCO 目标检测 、人体关键点检测评价指标
  • 【GPU】

  1. Machine learning — Is the emperor wearing clothes? ↩︎

你可能感兴趣的:(CNN,Paper)