图像识别 Image Recognition 专知荟萃

入门学习

1. 如何识别图像边缘？  阮一峰
   • [http://www.ruanyifeng.com/blog/2016/07/edge-recognition.html]
2. CS231n课程笔记翻译：图像分类笔记
   • [http://cs231n.github.io/classification/]
   • [https://zhuanlan.zhihu.com/p/20894041]
3. 深度学习、图像分类入门，从VGG16卷积神经网络开始 [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) 翻译
   • [http://blog.csdn.net/darkprince120/article/details/53024714]
5. 深度学习框架Caffe图片分类教程
   • [http://blog.csdn.net/qq_31258245/article/details/75093380]
6. MobileNet教程：用TensorFlow搭建在手机上运行的图像分类器
   • [https://zhuanlan.zhihu.com/p/28199892]
7. 图像验证码和大规模图像识别技术
   • [http://www.infoq.com/cn/articles/CAPTCHA-image-recognition]
8. 卷积神经网络如何进行图像识别
   • [http://www.infoq.com/cn/articles/convolutional-neural-networks-image-recognition]
9. 图像识别与验证码
   • [https://zhuanlan.zhihu.com/securityCode]
10. 图像识别(知乎话题) - [https://www.zhihu.com/topic/19588774/top-answers?page=1]

综述

1. A Review of Image Recognition with Deep Convolutional Neural Network
   • [https://link.springer.com/chapter/10.1007/978-3-319-63309-1_7]
2. Review on Image Recognition
   • [http://pnrsolution.org/Datacenter/Vol3/Issue2/186.pdf]
3. 深度学习在图像识别中的研究进展与展望
   • [https://piazza-resources.s3.amazonaws.com/i48o74a0lqu0/i4fcg2o44k63n6/deep_recognition.pdf?AWSAccessKeyId=AKIAIEDNRLJ4AZKBW6HA&Expires=1509460321&Signature=DxZ8LrEEStKQrKESDufA7i3qIGA%3D]
4. 图像物体分类与检测算法综述 黄凯奇 任伟强 谭铁牛 [http://cjc.ict.ac.cn/online/cre/hkq-2014526115913.pdf]
5. Book Chapter - Objecter Recognition
   • [http://www.cse.usf.edu/~r1k/MachineVisionBook/MachineVision.files/MachineVision_Chapter15.pdf]

进阶文章

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
   • [http://arxiv.org/abs/1310.1531]

2014

1. CNN Features off-the-shelf: an Astounding Baseline for Recognition CVPR 2014
   • [http://arxiv.org/abs/1403.6382]
2. Deeply learned face representations are sparse, selective, and robust
   • [http://arxiv.org/abs/1412.1265]
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
   • [http://mmlab.ie.cuhk.edu.hk/pdf/YiSun_CVPR14.pdf]
5. Multiple Object Recognition with Visual Attention**
   • [https://arxiv.org/abs/1412.7755]

2015

1. HD-CNN: Hierarchical Deep Convolutional Neural Network for Image Classification intro: ICCV 2015
   • [https://arxiv.org/abs/1410.0736]
2. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. ImageNet top-5 error: 4.94%
   • [http://arxiv.org/abs/1502.01852]
3. Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios
   • [http://ieeexplore.ieee.org/document/7486476/]
4. FaceNet: A Unified Embedding for Face Recognition and Clustering
   • [http://arxiv.org/abs/1503.03832]

2016

1. Humans and deep networks largely agree on which kinds of variation make object recognition harder**
   • [http://arxiv.org/abs/1604.06486]
2. FusionNet: 3D Object Classification Using Multiple Data Representations
   • [https://arxiv.org/abs/1607.05695]
3. Deep FisherNet for Object Classification**
   • [http://arxiv.org/abs/1608.00182]
4. Factorized Bilinear Models for Image Recognition**
   • [https://arxiv.org/abs/1611.05709]
5. Hyperspectral CNN Classification with Limited Training Samples**
   • [https://arxiv.org/abs/1611.09007]
6. The More You Know: Using Knowledge Graphs for Image Classification**
   • [https://arxiv.org/abs/1612.04844]
7. MaxMin Convolutional Neural Networks for Image Classification**
   • [http://webia.lip6.fr/~thomen/papers/Blot_ICIP_2016.pdf]
8. Cost-Effective Active Learning for Deep Image Classification. TCSVT 2016.
   • [https://arxiv.org/abs/1701.03551]
9. DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment
   • [http://arxiv.org/abs/1606.05675]

2017

1. Deep Collaborative Learning for Visual Recognition
   • [https://www.arxiv.org/abs/1703.01229]
2. Bilinear CNN Models for Fine-grained Visual Recognition
   • [http://vis-www.cs.umass.edu/bcnn/]
3. Multiple Instance Learning Convolutional Neural Networks for Object Recognition**
   • [https://arxiv.org/abs/1610.03155]
4. B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
   • [https://arxiv.org/abs/1709.09890](
5. Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification
   • [https://arxiv.org/abs/1709.03439]
6. Deep Mixture of Diverse Experts for Large-Scale Visual Recognition
   • [https://arxiv.org/abs/1706.07901]
     Sunrise or Sunset: Selective Comparison Learning for Subtle Attribute Recognition
   • [https://arxiv.org/abs/1707.06335]
7. Convolutional Low-Resolution Fine-Grained Classification
   • [https://arxiv.org/abs/1703.05393]

Tutorial

1. CVPR tutorial : Large-Scale Visual Recognition
   • [http://www.europe.naverlabs.com/Research/Computer-Vision/Highlights/CVPR-tutorial-Large-Scale-Visual-Recognition]
2. Image Recognition with Tensorflow
   • [https://www.tensorflow.org/tutorials/image_recognition]
3. Visual Object Recognition Tutorial by Bastian Leibe & Kristen Grauman
   • [https://www.google.com.au/url?sa=t&rct=j&q=&esrc=s&source=web&cd=32&cad=rja&uact=8&ved=0ahUKEwiWrq3W5JrXAhWFLpQKHQPuCcI4HhAWCC8wAQ&url=http%3A%2F%2Fz.cs.utexas.edu%2Fusers%2Fpiyushk%2Fcourses%2Fspr12%2Fslides%2FAAAI-tutorial-2.ppt&usg=AOvVaw3tQkyK0zW7nZ28LhrGzCUC]

视频教程

1. CS231n: Convolutional Neural Networks for Visual Recognition
   • [http://cs231n.stanford.edu/]
2. 李飞飞: 我们怎么教计算机理解图片？
   - [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)

代码

1. AlexNet 
   • [https://github.com/BVLC/caffe/tree/master/models/bvlc_alexnet]
2. ZFnet [https://github.com/rainer85ah/Papers2Code/tree/master/ZFNet]
3. VGG
   • [https://github.com/machrisaa/tensorflow-vgg]
4. GoogLeNet [https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet]
5. ResNet
   • [https://github.com/KaimingHe/deep-residual-networks]
6. HD-CNN
   • [https://sites.google.com/site/homepagezhichengyan/home/hdcnn/code]
7. Factorized Bilinear Models for Image Recognition
   • [https://github.com/lyttonhao/Factorized-Bilinear-Network]
8. MaxMin Convolutional Neural Networks for Image Classification
   • [https://github.com/karandesai-96/maxmin-cnn]
9. Multiple Object Recognition with Visual Attention
   • [https://github.com/jrbtaylor/visual-attention]
10. Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
    • [https://github.com/zhufengx/SRN_multilabel/]
11. Deep Learning Face Representation from Predicting 10,000 Classes
    • [https://github.com/stdcoutzyx/DeepID_FaceClassify]
12. FaceNet: A Unified Embedding for Face Recognition and Clustering
    • [https://github.com/davidsandberg/facenet]
13. DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment
    • [https://github.com/deercoder/DeepFood]

领域专家

1. Yangqing Jia
   • [http://daggerfs.com/]
2. Ross Girshick
   • [http://www.rossgirshick.info/]
3. Xiaodi Hou
   • [http://www.houxiaodi.com/]
4. Kaiming He
   • [http://kaiminghe.com/]
5. Jian Sun
   • [http://www.jiansun.org/]
6. Xiaoou Tang
   • [https://www.ie.cuhk.edu.hk/people/xotang.shtml]
7. Shuicheng Yan
   • [https://www.ece.nus.edu.sg/stfpage/eleyans/]

---

初步版本，水平有限，有错误或者不完善的地方，欢迎大家提建议和补充，会一直保持更新，本文为专知内容组原创内容，未经允许不得转载，如需转载请发送邮件至fangquanyi@gmail.com 或 联系微信专知小助手（Rancho_Fang）

敬请关注http://www.zhuanzhi.ai 和关注专知公众号，获取第一手AI相关知识