從圖像中提取出有意義、有實用價值的信息。

圖像識別 Image Recognition 專知薈萃

入門學習

  1. 如何識別圖像邊緣? 阮一峰
  2. CS231n課程筆記翻譯:圖像分類筆記
  3. 深度學習、圖像分類入門,從VGG16卷積神經網絡開始 [http://blog.csdn.net/Errors_In_Life/article/details/65950699]
  4. The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3) 翻譯
  5. 深度學習框架Caffe圖片分類教程
  6. MobileNet教程:用TensorFlow搭建在手機上運行的圖像分類器
  7. 圖像驗證碼和大規模圖像識別技術
  8. 卷積神經網絡如何進行圖像識別
  9. 圖像識別與驗證碼
  10. 圖像識別(知乎話題) - [https://www.zhihu.com/topic/19588774/top-answers?page=1]

綜述

  1. A Review of Image Recognition with Deep Convolutional Neural Network
  2. Review on Image Recognition
  3. 深度學習在圖像識別中的研究進展與展望
  4. 圖像物體分類與檢測算法綜述 黃凱奇 任偉強 譚鐵牛 [http://cjc.ict.ac.cn/online/cre/hkq-2014526115913.pdf]
  5. Book Chapter - Objecter Recognition

進階文章

Imagenet result

  1. Microsoft (Deep Residual Learning] [http://arxiv.org/pdf/1512.03385v1.pdf]][[Slide](http://image-net.org/challenges/talks/ilsvrc2015_deep_residual_learning_kaiminghe.pdf] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition, arXiv:1512.03385.
  2. Microsoft (PReLu/Weight Initialization] [http://arxiv.org/pdf/1502.01852] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, arXiv:1502.01852.
  3. Batch Normalization [http://arxiv.org/pdf/1502.03167] Sergey Ioffe, Christian Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arXiv:1502.03167.
  4. GoogLeNet [http://arxiv.org/pdf/1409.4842] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, CVPR, 2015.
  5. VGG-Net [http://www.robots.ox.ac.uk/~vgg/research/very_deep/] [http://arxiv.org/pdf/1409.1556] Karen Simonyan and Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Visual Recognition, ICLR, 2015.
  6. AlexNet [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-25-2012] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, NIPS, 2012.

2013

  1. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, Trevor Darrell

2014

  1. CNN Features off-the-shelf: an Astounding Baseline for Recognition CVPR 2014
  2. Deeply learned face representations are sparse, selective, and robust
  3. Deep Learning Face Representation by Joint Identification-Verification
    - [https://arxiv.org/abs/1406.4773]
  4. Deep Learning Face Representation from Predicting 10,000 Classes. intro: CVPR 2014
  5. Multiple Object Recognition with Visual Attention**

2015

  1. HD-CNN: Hierarchical Deep Convolutional Neural Network for Image Classification intro: ICCV 2015
  2. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. ImageNet top-5 error: 4.94%
  3. Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios
  4. FaceNet: A Unified Embedding for Face Recognition and Clustering

2016

  1. Humans and deep networks largely agree on which kinds of variation make object recognition harder**
  2. FusionNet: 3D Object Classification Using Multiple Data Representations
  3. Deep FisherNet for Object Classification**
  4. Factorized Bilinear Models for Image Recognition**
  5. Hyperspectral CNN Classification with Limited Training Samples**
  6. The More You Know: Using Knowledge Graphs for Image Classification**
  7. MaxMin Convolutional Neural Networks for Image Classification**
  8. Cost-Effective Active Learning for Deep Image Classification. TCSVT 2016.
  9. DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment

2017

  1. Deep Collaborative Learning for Visual Recognition
  2. Bilinear CNN Models for Fine-grained Visual Recognition
  3. Multiple Instance Learning Convolutional Neural Networks for Object Recognition**
  4. B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
  5. Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification
  6. Deep Mixture of Diverse Experts for Large-Scale Visual Recognition
  7. Convolutional Low-Resolution Fine-Grained Classification

Tutorial

  1. CVPR tutorial : Large-Scale Visual Recognition
  2. Image Recognition with Tensorflow
  3. Visual Object Recognition Tutorial by Bastian Leibe & Kristen Grauman

視頻教程

  1. CS231n: Convolutional Neural Networks for Visual Recognition
  2. 李飛飛: 我們怎麼教計算機理解圖片?
    - [https://www.youtube.com/watch?v=40riCqvRoMs]

Datasets

  1. MNIST: handwritten digits (http://yann.lecun.com/exdb/mnist/)
  2. NIST: similar to MNIST, but larger
  3. Perturbed NIST: a dataset developed in Yoshua’s class (NIST with tons of deformations)
  4. CIFAR10 / CIFAR100: 32×32 natural image dataset with 10/100 categories (http://www.cs.utoronto.ca/~kriz/cifar.html)
  5. Caltech 101: pictures of objects belonging to 101 categories (http://www.vision.caltech.edu/Image_Datasets/Caltech101/)
  6. Caltech 256: pictures of objects belonging to 256 categories (http://www.vision.caltech.edu/Image_Datasets/Caltech256/)
  7. Caltech Silhouettes: 28×28 binary images contains silhouettes of the Caltech 101 dataset
  8. STL-10 dataset is an image recognition dataset for developing unsupervised feature learning, deep learning, self-taught learning algorithms. It is inspired by the CIFAR-10 dataset but with some modifications.http://www.stanford.edu/~acoates//stl10/
  9. The Street View House Numbers (SVHN) Dataset –http://ufldl.stanford.edu/housenumbers/
  10. NORB: binocular images of toy figurines under various illumination and pose (http://www.cs.nyu.edu/~ylclab/data/norb-v1.0/)
  11. Imagenet: image database organized according to the WordNethierarchy (http://www.image-net.org/)
  12. Pascal VOC: various object recognition challenges (http://pascallin.ecs.soton.ac.uk/challenges/VOC/)
  13. Labelme: A large dataset of annotated images,http://labelme.csail.mit.edu/Release3.0/browserTools/php/dataset.php
  14. COIL 20: different objects imaged at every angle in a 360 rotation(http://www.cs.columbia.edu/CAVE/software/softlib/coil-20.php)
  15. COIL100: different objects imaged at every angle in a 360 rotation (http://www1.cs.columbia.edu/CAVE/software/softlib/coil-100.php)

代碼

  1. AlexNet
  2. ZFnet [https://github.com/rainer85ah/Papers2Code/tree/master/ZFNet]
  3. VGG
  4. GoogLeNet [https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet]
  5. ResNet
  6. HD-CNN
  7. Factorized Bilinear Models for Image Recognition
  8. MaxMin Convolutional Neural Networks for Image Classification
  9. Multiple Object Recognition with Visual Attention
  10. Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
  11. Deep Learning Face Representation from Predicting 10,000 Classes
  12. FaceNet: A Unified Embedding for Face Recognition and Clustering
  13. DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment

領域專家

  1. Yangqing Jia
  2. Ross Girshick
  3. Xiaodi Hou
  4. Kaiming He
  5. Jian Sun
  6. Xiaoou Tang
  7. Shuicheng Yan

初步版本,水平有限,有錯誤或者不完善的地方,歡迎大家提建議和補充,會一直保持更新,本文為專知內容組原創內容,未經允許不得轉載,如需轉載請發送郵件至fangquanyi@gmail.com或 聯係微信專知小助手(Rancho_Fang)

敬請關注//www.webtourguide.com和關注專知公眾號,獲取第一手AI相關知識

成為VIP會員查看完整內容
Top