126篇殿堂级深度学习论文分类整理从入门到应用_[#第一枪]

发布时间：2021-06-07 15:00:37 阅读：次来源：镗床厂家

如果你有非常大的决心从事深度学习，又不想在这一行打酱油，那么研读大牛论文将是不可避免的一步。而作为新人，你的第一个问题或许是：“论文那么多，从哪一篇读起？”

本文将试图解决这个问题——文章标题本来是：“从入门到绝望，无止境的深度学习论文”。请诸位备好道具，开启头悬梁锥刺股的学霸姿势。

开个玩笑。

但对非科班出身的开发者而言，读论文的确可以成为一件很痛苦的事。但好消息来了——为避免初学者陷入迷途苦海，昵称为 songrotek 的学霸在 GitHub 发布了他整理的深度学习路线图，分门别类梳理了新入门者最需要学习的 DL 论文，又按重要程度给每篇论文打上星星。

截至目前，这份 DL 论文路线图已在 GitHub 收获了近万颗星星好评，人气极高。雷锋网感到非常有必要对大家进行介绍。

闲话少说，该路线图根据以下四项原则而组织：

从大纲到细节

从经典到前沿

从一般到具体领域

关注最新研究突破

作者注：有许多论文很新但非常值得一读。

1 深度学习历史和基础1.0 书籍

█[0]Bengio, Yoshua, Ian J. Goodfellow, and Aaron Courville. "Deep learning." An MIT Press book. (2015).[pdf](Ian Goodfellow 等大牛所著的教科书，乃深度学习圣经。你可以同时研习这本书以及以下论文)★★★★★

地址：https://github.com/HFTrader/DeepLearningBook/raw/master/DeepLearningBook.pdf

1.1 调查

█[1]LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015): 436-444.[pdf](三巨头做的调查)★★★★★

地址：http://www.cs.toronto.edu/~hinton/absps/NatureDeepReview.pdf

1.2 深度置信网络 (DBN，深度学习前夜的里程碑)

█[2]Hinton, Geoffrey E., Simon Osindero, and Yee-Whye Teh. "A fast learning algorithm for deep belief nets." Neural computation 18.7 (2006): 1527-1554.[pdf] (深度学习前夜)★★★

地址：http://www.cs.toronto.edu/~hinton/absps/ncfast.pdf

█[3]Hinton, Geoffrey E., and Ruslan R. Salakhutdinov. "Reducing the dimensionality of data with neural networks." Science 313.5786 (2006): 504-507.[pdf](里程碑，展示了深度学习的前景)★★★

地址：http://www.cs.toronto.edu/~hinton/science.pdf

1.3 ImageNet 的进化（深度学习从此萌发）

█[4]Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.[pdf](AlexNet, 深度学习突破)★★★★★

地址：http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

█[5]Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).[pdf](VGGNet，神经网络变得很深层)★★★

地址：https://arxiv.org/pdf/1409.1556.pdf

█[6]Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015.[pdf](GoogLeNet)★★★

地址：http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf

█[7]He, Kaiming, et al. "Deep residual learning for image recognition." arXiv preprint arXiv:1512.03385 (2015).[pdf](ResNet，特别深的神经网络, CVPR 最佳论文)★★★★★

地址：https://arxiv.org/pdf/1512.03385.pdf

1.4 语音识别的进化

█[8]Hinton, Geoffrey, et al. "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups." IEEE Signal Processing Magazine 29.6 (2012): 82-97.[pdf](语音识别的突破) ★★★★

地址：http://cs224d.stanford.edu/papers/maas_paper.pdf

█[9]Graves, Alex, Abdel-rahman Mohamed, and Geoffrey Hinton. "Speech recognition with deep recurrent neural networks." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013.[pdf](RNN) ★★★

地址：http://arxiv.org/pdf/1303.5778.pdf

█[10]Graves, Alex, and Navdeep Jaitly. "Towards End-To-End Speech Recognition with Recurrent Neural Networks." ICML. Vol. 14. 2014.[pdf] ★★★

地址：http://www.jmlr.org/proceedings/papers/v32/graves14.pdf

█[11]Sak, Ha?im, et al. "Fast and accurate recurrent neural network acoustic models for speech recognition." arXiv preprint arXiv:1507.06947 (2015).[pdf](谷歌语音识别系统)★★★

地址：http://arxiv.org/pdf/1507.06947

█[12]Amodei, Dario, et al. "Deep speech 2: End-to-end speech recognition in english and mandarin." arXiv preprint arXiv:1512.02595 (2015).[pdf](百度语音识别系统)★★★★

地址：https://arxiv.org/pdf/1512.02595.pdf

█[13]W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig "Achieving Human Parity in Conversational Speech Recognition." arXiv preprint arXiv:1610.05256 (2016).[pdf](最前沿的语音识别, 微软)★★★★

地址：https://arxiv.org/pdf/1610.05256v1

研读以上论文之后，你将对深度学习历史、模型的基本架构（包括 CNN, RNN, LSTM）有一个基础的了解，并理解深度学习如何应用于图像和语音识别问题。接下来的论文，将带你深入探索深度学习方法、在不同领域的应用和前沿尖端技术。我建议，你可以根据兴趣和工作/研究方向进行选择性的阅读。

2 深度学习方法2.1 模型

█[14]Hinton, Geoffrey E., et al. "Improving neural networks by preventing co-adaptation of feature detectors." arXiv preprint arXiv:1207.0580 (2012).[pdf](Dropout)★★★

地址：https://arxiv.org/pdf/1207.0580.pdf

█[15]Srivastava, Nitish, et al. "Dropout: a simple way to prevent neural networks from overfitting." Journal of Machine Learning Research 15.1 (2014): 1929-1958.[pdf]★★★

地址：http://www.jmlr.org/papers/volume15/srivastava14a.old/source/srivastava14a.pdf

█[16]Ioffe, Sergey, and Christian Szegedy. "Batch normalization: Accelerating deep network training by reducing internal covariate shift." arXiv preprint arXiv:1502.03167 (2015).[pdf](2015 年的杰出研究)★★★★

地址：http://arxiv.org/pdf/1502.03167

█[17]Ba, Jimmy Lei, Jamie Ryan Kiros, and Geoffrey E. Hinton. "Layer normalization." arXiv preprint arXiv:1607.06450 (2016).[pdf](Batch Normalization 的更新)★★★★

地址：https://arxiv.org/pdf/1607.06450.pdf?utm_source=sciontist.com&utm_medium=refer&utm_campaign=promote

█[18]Courbariaux, Matthieu, et al. "Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to+ 1 or?1."[pdf](新模型，快)★★★

地址：https://pdfs.semanticscholar.org/f832/b16cb367802609d91d400085eb87d630212a.pdf

█[19]Jaderberg, Max, et al. "Decoupled neural interfaces using synthetic gradients." arXiv preprint arXiv:1608.05343 (2016).[pdf](训练方法的创新，研究相当不错)★★★★★

地址：https://arxiv.org/pdf/1608.05343

█[20]Chen, Tianqi, Ian Goodfellow, and Jonathon Shlens. "Net2net: Accelerating learning via knowledge transfer." arXiv preprint arXiv:1511.05641 (2015).[pdf](改进此前的训练网络，来缩短训练周期)★★★

地址：https://arxiv.org/abs/1511.05641

█[21]Wei, Tao, et al. "Network Morphism." arXiv preprint arXiv:1603.01670 (2016).[pdf](改进此前的训练网络，来缩短训练周期)★★★

地址：https://arxiv.org/abs/1603.01670

2.2 优化 Optimization

█[22]Sutskever, Ilya, et al. "On the importance of initialization and momentum in deep learning." ICML (3) 28 (2013): 1139-1147.[pdf](Momentum optimizer)★★

地址：http://www.jmlr.org/proceedings/papers/v28/sutskever13.pdf

█[23]Kingma, Diederik, and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014).[pdf](Maybe used most often currently)★★★

地址：http://arxiv.org/pdf/1412.6980

█[24]Andrychowicz, Marcin, et al. "Learning to learn by gradient descent by gradient descent." arXiv preprint arXiv:1606.04474 (2016).[pdf](Neural Optimizer,Amazing Work)★★★★★

地址：https://arxiv.org/pdf/1606.04474

█[25]Han, Song, Huizi Mao, and William J. Dally. "Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding." CoRR, abs/1510.00149 2 (2015).[pdf](ICLR best paper, new direction to make NN running fast,DeePhi Tech Startup)★★★★★

地址：https://pdfs.semanticscholar.org/5b6c/9dda1d88095fa4aac1507348e498a1f2e863.pdf

█[26]Iandola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size." arXiv preprint arXiv:1602.07360 (2016).[pdf](Also a new direction to optimize NN,DeePhi Tech Startup)★★★★

地址：http://arxiv.org/pdf/1602.07360

2.3 无监督学习/深度生成模型

█[27]Le, Quoc V. "Building high-level features using large scale unsupervised learning." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013.[pdf](里程碑, 吴恩达, 谷歌大脑, Cat)★★★★

地址：http://arxiv.org/pdf/1112.6209.pdf&embed

█[28]Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." arXiv preprint arXiv:1312.6114 (2013).[pdf](VAE)★★★★

地址：http://arxiv.org/pdf/1312.6114

█[29]Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014.[pdf](GAN，很酷的想法)★★★★★

地址：http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf

█[30]Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015).[pdf](DCGAN)★★★★

地址：http://arxiv.org/pdf/1511.06434

█[31]Gregor, Karol, et al. "DRAW: A recurrent neural network for image generation." arXiv preprint arXiv:1502.04623 (2015).[pdf](VAE with attention, 很出色的研究)★★★★★

地址：http://jmlr.org/proceedings/papers/v37/gregor15.pdf

█[32]Oord, Aaron van den, Nal Kalchbrenner, and Koray Kavukcuoglu. "Pixel recurrent neural networks." arXiv preprint arXiv:1601.06759 (2016).[pdf](PixelRNN)★★★★

地址：http://arxiv.org/pdf/1601.06759

█[33]Oord, Aaron van den, et al. "Conditional image generation with PixelCNN decoders." arXiv preprint arXiv:1606.05328 (2016).[pdf](PixelCNN)★★★★

地址：https://arxiv.org/pdf/1606.05328

2.4 递归神经网络（RNN） / Sequence-to-Sequence Model

█[34]Graves, Alex. "Generating sequences with recurrent neural networks." arXiv preprint arXiv:1308.0850 (2013).[pdf](LSTM, 效果很好，展示了 RNN 的性能)★★★★

地址：http://arxiv.org/pdf/1308.0850

█[35]Cho, Kyunghyun, et al. "Learning phrase representations using RNN encoder-decoder for statistical machine translation." arXiv preprint arXiv:1406.1078 (2014).[pdf](第一篇 Sequence-to-Sequence 的论文)★★★★

地址：http://arxiv.org/pdf/1406.1078

█[36]Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. "Sequence to sequence learning with neural networks." Advances in neural information processing systems. 2014.[pdf](杰出研究)★★★★★

地址：http://papers.nips.cc/paper/5346-information-based-learning-by-agents-in-unbounded-state-spaces.pdf

█[37]Bahdanau, Dzmitry, KyungHyun Cho, and Yoshua Bengio. "Neural Machine Translation by Jointly Learning to Align and Translate." arXiv preprint arXiv:1409.0473 (2014).[pdf]★★★★

地址：https://arxiv.org/pdf/1409.0473v7.pdf

█[38]Vinyals, Oriol, and Quoc Le. "A neural conversational model." arXiv preprint arXiv:1506.05869 (2015).[pdf](Seq-to-Seq 聊天机器人)★★★

地址：http://arxiv.org/pdf/1506.05869.pdf%20(http://arxiv.org/pdf/1506.05869.pdf)

2.5 神经网络图灵机

█[39]Graves, Alex, Greg Wayne, and Ivo Danihelka. "Neural turing machines." arXiv preprint arXiv:1410.5401 (2014).[pdf] (未来计算机的基础原型机)★★★★★

地址：http://arxiv.org/pdf/1410.5401.pdf

█[40]Zaremba, Wojciech, and Ilya Sutskever. "Reinforcement learning neural Turing machines." arXiv preprint arXiv:1505.00521 362 (2015).[pdf]★★★

地址：https://pdfs.semanticscholar.org/f10e/071292d593fef939e6ef4a59baf0bb3a6c2b.pdf

█[41]Weston, Jason, Sumit Chopra, and Antoine Bordes. "Memory networks." arXiv preprint arXiv:1410.3916 (2014).[pdf]★★★

地址：http://arxiv.org/pdf/1410.3916

█[42]Sukhbaatar, Sainbayar, Jason Weston, and Rob Fergus. "End-to-end memory networks." Advances in neural information processing systems. 2015.[pdf]★★★★

地址：http://papers.nips.cc/paper/5846-end-to-end-memory-networks.pdf

█[43]Vinyals, Oriol, Meire Fortunato, and Navdeep Jaitly. "Pointer networks." Advances in Neural Information Processing Systems. 2015.[pdf]★★★★

地址：http://papers.nips.cc/paper/5866-pointer-networks.pdf

█[44]Graves, Alex, et al. "Hybrid computing using a neural network with dynamic external memory." Nature (2016).[pdf] (里程碑，把以上论文的想法整合了起来)★★★★★

地址：https://www.dropbox.com/s/0a40xi702grx3dq/2016-graves.pdf

2.6 深度强化学习

█[45]Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." arXiv preprint arXiv:1312.5602 (2013).[pdf])(第一个以深度强化学习为题的论文)★★★★

地址：http://arxiv.org/pdf/1312.5602.pdf

█[46]Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." Nature 518.7540 (2015): 529-533.[pdf](里程碑)★★★★★

地址：https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf

█[47]Wang, Ziyu, Nando de Freitas, and Marc Lanctot. "Dueling network architectures for deep reinforcement learning." arXiv preprint arXiv:1511.06581 (2015).[pdf](ICLR 最佳论文，很棒的想法)★★★★

地址：http://arxiv.org/pdf/1511.06581

█[48]Mnih, Volodymyr, et al. "Asynchronous methods for deep reinforcement learning." arXiv preprint arXiv:1602.01783 (2016).[pdf](前沿方法)★★★★★

地址：http://arxiv.org/pdf/1602.01783

█[49]Lillicrap, Timothy P., et al. "Continuous control with deep reinforcement learning." arXiv preprint arXiv:1509.02971 (2015).[pdf](DDPG)★★★★

地址：http://arxiv.org/pdf/1509.02971

█[50]Gu, Shixiang, et al. "Continuous Deep Q-Learning with Model-based Acceleration." arXiv preprint arXiv:1603.00748 (2016).[pdf](NAF)★★★★

地址：http://arxiv.org/pdf/1603.00748

█[51]Schulman, John, et al. "Trust region policy optimization." CoRR, abs/1502.05477 (2015).[pdf](TRPO)★★★★

地址：http://www.jmlr.org/proceedings/papers/v37/schulman15.pdf

█[52]Silver, David, et al. "Mastering the game of Go with deep neural networks and tree search." Nature 529.7587 (2016): 484-489.[pdf](AlphaGo)★★★★★

地址：http://willamette.edu/~levenick/cs448/goNature.pdf

2.7 深度迁移学习 /终生学习 / 强化学习

█[53]Bengio, Yoshua. "Deep Learning of Representations for Unsupervised and Transfer Learning." ICML Unsupervised and Transfer Learning 27 (2012): 17-36.[pdf](这是一个教程)★★★

地址：http://www.jmlr.org/proceedings/papers/v27/bengio12a/bengio12a.pdf

█[54]Silver, Daniel L., Qiang Yang, and Lianghao Li. "Lifelong Machine Learning Systems: Beyond Learning Algorithms." AAAI Spring Symposium: Lifelong Machine Learning. 2013.[pdf](对终生学习的简单讨论)★★★

地址：http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.696.7800&rep=rep1&type=pdf

█[55]Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. "Distilling the knowledge in a neural network." arXiv preprint arXiv:1503.02531 (2015).[pdf](大神们的研究)★★★★

地址：http://arxiv.org/pdf/1503.02531

█[56]Rusu, Andrei A., et al. "Policy distillation." arXiv preprint arXiv:1511.06295 (2015).[pdf](RL 领域)★★★

地址：http://arxiv.org/pdf/1511.06295

█[57]Parisotto, Emilio, Jimmy Lei Ba, and Ruslan Salakhu★★★tdinov. "Actor-mimic: Deep multitask and transfer reinforcement learning." arXiv preprint arXiv:1511.06342 (2015).[pdf](RL 领域)★★★

地址：http://arxiv.org/pdf/1511.06342

█[58]Rusu, Andrei A., et al. "Progressive neural networks." arXiv preprint arXiv:1606.04671 (2016).[pdf](杰出研究, 很新奇的想法)★★★★★

地址：https://arxiv.org/pdf/1606.04671

2.8 One Shot 深度学习

█[59]Lake, Brenden M., Ruslan Salakhutdinov, and Joshua B. Tenenbaum. "Human-level concept learning through probabilistic program induction." Science 350.6266 (2015): 1332-1338.[pdf](不含深度学习但值得一读)★★★★★

地址：http://clm.utexas.edu/compjclub/wp-content/uploads/2016/02/lake2015.pdf

█[60]Koch, Gregory, Richard Zemel, and Ruslan Salakhutdinov. "Siamese Neural Networks for One-shot Image Recognition."(2015)[pdf]★★★

地址：http://www.cs.utoronto.ca/~gkoch/files/msc-thesis.pdf

█[61]Santoro, Adam, et al. "One-shot Learning with Memory-Augmented Neural Networks." arXiv preprint arXiv:1605.06065 (2016).[pdf](one shot 学习的基础一步)★★★★

地址：http://arxiv.org/pdf/1605.06065

█[62]Vinyals, Oriol, et al. "Matching Networks for One Shot Learning." arXiv preprint arXiv:1606.04080 (2016).[pdf]★★★

地址：https://arxiv.org/pdf/1606.04080

█[63]Hariharan, Bharath, and Ross Girshick. "Low-shot visual object recognition." arXiv preprint arXiv:1606.02819 (2016).[pdf] (通向更大规模数据的一步)★★★★

地址：http://arxiv.org/pdf/1606.02819

3 应用3.1 自然语言处理 (NLP)

█[1]Antoine Bordes, et al. "Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing." AISTATS(2012)[pdf]★★★★

地址：https://www.hds.utc.fr/~bordesan/dokuwiki/lib/exe/fetch.php?id=en%3Apubli&cache=cache&media=en:bordes12aistats.pdf

█[2]Mikolov, et al. "Distributed representations of words and phrases and their compositionality." ANIPS(2013): 3111-3119[pdf](word2vec)★★★

地址：http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf

█[3]Sutskever, et al. "“Sequence to sequence learning with neural networks." ANIPS(2014)[pdf] ★★★

地址：http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf

█[4]Ankit Kumar, et al. "“Ask Me Anything: Dynamic Memory Networks for Natural Language Processing." arXiv preprint arXiv:1506.07285(2015)[pdf]★★★★

地址：https://arxiv.org/abs/1506.07285

█[5]Yoon Kim, et al. "Character-Aware Neural Language Models." NIPS(2015) arXiv preprint arXiv:1508.06615(2015)[pdf]★★★

地址：https://arxiv.org/abs/1508.06615

█[6]Jason Weston, et al. "Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks." arXiv preprint arXiv:1502.05698(2015)[pdf](bAbI tasks)★★★

地址：https://arxiv.org/abs/1502.05698

█[7]Karl Moritz Hermann, et al. "Teaching Machines to Read and Comprehend." arXiv preprint arXiv:1506.03340(2015)[pdf](CNN/每日邮报完形填空风格的问题)★★

地址：https://arxiv.org/abs/1506.03340

█[8]Alexis Conneau, et al. "Very Deep Convolutional Networks for Natural Language Processing." arXiv preprint arXiv:1606.01781(2016)[pdf](文本分类的前沿技术)★★★

地址：https://arxiv.org/abs/1606.01781

█[9]Armand Joulin, et al. "Bag of Tricks for Efficient Text Classification." arXiv preprint arXiv:1607.01759(2016)[pdf](比前沿技术稍落后, 但快很多)★★★

地址：https://arxiv.org/abs/1607.01759

3.2 物体检测

█[1]Szegedy, Christian, Alexander Toshev, and Dumitru Erhan. "Deep neural networks for object detection." Advances in Neural Information Processing Systems. 2013.[pdf]★★★

地址：http://papers.nips.cc/paper/5207-deep-neural-networks-for-object-detection.pdf

█[2]Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.[pdf](RCNN)★★★★★

地址：http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Girshick_Rich_Feature_Hierarchies_2014_CVPR_paper.pdf

█[3]He, Kaiming, et al. "Spatial pyramid pooling in deep convolutional networks for visual recognition." European Conference on Computer Vision. Springer International Publishing, 2014.[pdf](SPPNet)★★★★

地址：http://arxiv.org/pdf/1406.4729

█[4]Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE International Conference on Computer Vision. 2015.[pdf]★★★★

地址：https://pdfs.semanticscholar.org/8f67/64a59f0d17081f2a2a9d06f4ed1cdea1a0ad.pdf

█[5]Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object detection with region proposal networks." Advances in neural information processing systems. 2015.[pdf]★★★★

地址：http://papers.nips.cc/paper/5638-analysis-of-variational-bayesian-latent-dirichlet-allocation-weaker-sparsity-than-map.pdf

█[6]Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." arXiv preprint arXiv:1506.02640 (2015).[pdf](YOLO，杰出研究，非常具有使用价值）★★★★★

地址：http://homes.cs.washington.edu/~ali/papers/YOLO.pdf

█[7]Liu, Wei, et al. "SSD: Single Shot MultiBox Detector." arXiv preprint arXiv:1512.02325 (2015).[pdf]★★★

地址：http://arxiv.org/pdf/1512.02325

█[8]Dai, Jifeng, et al. "R-FCN: Object Detection via Region-based Fully Convolutional Networks." arXiv preprint arXiv:1605.06409 (2016).[pdf]★★★★

地址：https://arxiv.org/abs/1605.06409

3.3 视觉追踪

█[1]Wang, Naiyan, and Dit-Yan Yeung. "Learning a deep compact image representation for visual tracking." Advances in neural information processing systems. 2013.[pdf](第一篇使用深度学习做视觉追踪的论文，DLT Tracker)★★★

地址：http://papers.nips.cc/paper/5192-learning-a-deep-compact-image-representation-for-visual-tracking.pdf

█[2]Wang, Naiyan, et al. "Transferring rich feature hierarchies for robust visual tracking." arXiv preprint arXiv:1501.04587 (2015).[pdf](SO-DLT)★★★★

地址：http://arxiv.org/pdf/1501.04587

█[3]Wang, Lijun, et al. "Visual tracking with fully convolutional networks." Proceedings of the IEEE International Conference on Computer Vision. 2015.[pdf](FCNT)★★★★

地址：http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Wang_Visual_Tracking_With_ICCV_2015_paper.pdf

█[4]Held, David, Sebastian Thrun, and Silvio Savarese. "Learning to Track at 100 FPS with Deep Regression Networks." arXiv preprint arXiv:1604.01802 (2016).[pdf](GOTURN，在深度学习方法里算是非常快的，但仍比非深度学习方法慢很多)★★★★

地址：http://arxiv.org/pdf/1604.01802

█[5]Bertinetto, Luca, et al. "Fully-Convolutional Siamese Networks for Object Tracking." arXiv preprint arXiv:1606.09549 (2016).[pdf](SiameseFC，实时物体追踪领域的最新前沿技术)★★★★

地址：https://arxiv.org/pdf/1606.09549

█[6]Martin Danelljan, Andreas Robinson, Fahad Khan, Michael Felsberg. "Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking." ECCV (2016)[pdf](C-COT)★★★★

地址：http://www.cvl.isy.liu.se/research/objrec/visualtracking/conttrack/C-COT_ECCV16.pdf

█[7]Nam, Hyeonseob, Mooyeol Baek, and Bohyung Han. "Modeling and Propagating CNNs in a Tree Structure for Visual Tracking." arXiv preprint arXiv:1608.07242 (2016).[pdf](VOT2016 获奖论文,TCNN)★★★★

地址：https://arxiv.org/pdf/1608.07242

3.4 图像标注

█[1]Farhadi,Ali,etal. "Every picture tells a story: Generating sentences from images". In Computer VisionECCV 2010. Springer Berlin Heidelberg:15-29, 2010.[pdf]★★★

地址：https://www.cs.cmu.edu/~afarhadi/papers/sentence.pdf

█[2]Kulkarni, Girish, et al. "Baby talk: Understanding and generating image descriptions". In Proceedings of the 24th CVPR, 2011.[pdf] ★★★★

地址：http://tamaraberg.com/papers/generation_cvpr11.pdf

█[3]Vinyals, Oriol, et al. "Show and tell: A neural image caption generator". In arXiv preprint arXiv:1411.4555, 2014.[pdf] ★★★

地址：https://arxiv.org/pdf/1411.4555.pdf

█[4]Donahue, Jeff, et al. "Long-term recurrent convolutional networks for visual recognition and description". In arXiv preprint arXiv:1411.4389 ,2014.[pdf]

地址：https://arxiv.org/pdf/1411.4389.pdf

█[5]Karpathy, Andrej, and Li Fei-Fei. "Deep visual-semantic alignments for generating image descriptions". In arXiv preprint arXiv:1412.2306, 2014.[pdf] ★★★★★

地址：https://cs.stanford.edu/people/karpathy/cvpr2015.pdf

█[6]Karpathy, Andrej, Armand Joulin, and Fei Fei F. Li. "Deep fragment embeddings for bidirectional image sentence mapping". In Advances in neural information processing systems, 2014.[pdf] ★★★★

地址：https://arxiv.org/pdf/1406.5679v1.pdf

█[7]Fang, Hao, et al. "From captions to visual concepts and back". In arXiv preprint arXiv:1411.4952, 2014.[pdf] ★★★★★

地址：https://arxiv.org/pdf/1411.4952v3.pdf

█[8]Chen, Xinlei, and C. Lawrence Zitnick. "Learning a recurrent visual representation for image caption generation". In arXiv preprint arXiv:1411.5654, 2014.[pdf] ★★★★

地址：https://arxiv.org/pdf/1411.5654v1.pdf

█[9]Mao, Junhua, et al. "Deep captioning with multimodal recurrent neural networks (m-rnn)". In arXiv preprint arXiv:1412.6632, 2014.[pdf] ★★★

地址：https://arxiv.org/pdf/1412.6632v5.pdf

█[10]Xu, Kelvin, et al. "Show, attend and tell: Neural image caption generation with visual attention". In arXiv preprint arXiv:1502.03044, 2015.[pdf] ★★★★★

地址：https://arxiv.org/pdf/1502.03044v3.pdf

3.5 机器翻译

部分里程碑研究被列入 RNN / Seq-to-Seq 版块。

█[1]Luong, Minh-Thang, et al. "Addressing the rare word problem in neural machine translation." arXiv preprint arXiv:1410.8206 (2014).[pdf]★★★★

地址：http://arxiv.org/pdf/1410.8206

█[2]Sennrich, et al. "Neural Machine Translation of Rare Words with Subword Units". In arXiv preprint arXiv:1508.07909, 2015.[pdf] ★★★

地址：https://arxiv.org/pdf/1508.07909.pdf

█[3]Luong, Minh-Thang, Hieu Pham, and Christopher D. Manning. "Effective approaches to attention-based neural machine translation." arXiv preprint arXiv:1508.04025 (2015).[pdf]★★★★

地址：http://arxiv.org/pdf/1508.04025

█[4]Chung, et al. "A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation". In arXiv preprint arXiv:1603.06147, 2016.[pdf]★★

地址：https://arxiv.org/pdf/1603.06147.pdf

█[5]Lee, et al. "Fully Character-Level Neural Machine Translation without Explicit Segmentation". In arXiv preprint arXiv:1610.03017, 2016.[pdf]★★★★★

地址：https://arxiv.org/pdf/1610.03017.pdf

█[6]Wu, Schuster, Chen, Le, et al. "Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation". In arXiv preprint arXiv:1609.08144v2, 2016.[pdf](Milestone)★★★★

地址：https://arxiv.org/pdf/1609.08144v2.pdf

3.6 机器人

█[1]Koutník, Jan, et al. "Evolving large-scale neural networks for vision-based reinforcement learning." Proceedings of the 15th annual conference on Genetic and evolutionary computation. ACM, 2013.[pdf]★★★

地址：http://repository.supsi.ch/4550/1/koutnik2013gecco.pdf

█[2]Levine, Sergey, et al. "End-to-end training of deep visuomotor policies." Journal of Machine Learning Research 17.39 (2016): 1-40.[pdf]★★★★★

地址：http://www.jmlr.org/papers/volume17/15-522/15-522.pdf

█[3]Pinto, Lerrel, and Abhinav Gupta. "Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours." arXiv preprint arXiv:1509.06825 (2015).[pdf]★★★

地址：http://arxiv.org/pdf/1509.06825

█[4]Levine, Sergey, et al. "Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection." arXiv preprint arXiv:1603.02199 (2016).[pdf]★★★★

地址：http://arxiv.org/pdf/1603.02199

█[5]Zhu, Yuke, et al. "Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning." arXiv preprint arXiv:1609.05143 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1609.05143

█[6]Yahya, Ali, et al. "Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search." arXiv preprint arXiv:1610.00673 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1610.00673

█[7]Gu, Shixiang, et al. "Deep Reinforcement Learning for Robotic Manipulation." arXiv preprint arXiv:1610.00633 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1610.00633

█[8]A Rusu, M Vecerik, Thomas Roth?rl, N Heess, R Pascanu, R Hadsell."Sim-to-Real Robot Learning from Pixels with Progressive Nets." arXiv preprint arXiv:1610.04286 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1610.04286.pdf

█[9]Mirowski, Piotr, et al. "Learning to navigate in complex environments." arXiv preprint arXiv:1611.03673 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1611.03673

3.7 艺术

█[1]Mordvintsev, Alexander; Olah, Christopher; Tyka, Mike (2015). "Inceptionism: Going Deeper into Neural Networks". Google Research.[html](Deep Dream)★★★★

地址：https://research.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html

█[2]Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arXiv preprint arXiv:1508.06576 (2015).[pdf](杰出研究，迄今最成功的方法)★★★★★

地址：http://arxiv.org/pdf/1508.06576

█[3]Zhu, Jun-Yan, et al. "Generative Visual Manipulation on the Natural Image Manifold." European Conference on Computer Vision. Springer International Publishing, 2016.[pdf](iGAN)★★★★

地址：https://arxiv.org/pdf/1609.03552

█[4]Champandard, Alex J. "Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks." arXiv preprint arXiv:1603.01768 (2016).[pdf](Neural Doodle)★★★★

地址：http://arxiv.org/pdf/1603.01768

█[5]Zhang, Richard, Phillip Isola, and Alexei A. Efros. "Colorful Image Colorization." arXiv preprint arXiv:1603.08511 (2016).[pdf]★★★★

地址：http://arxiv.org/pdf/1603.08511

█[6]Johnson, Justin, Alexandre Alahi, and Li Fei-Fei. "Perceptual losses for real-time style transfer and super-resolution." arXiv preprint arXiv:1603.08155 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1603.08155.pdf

█[7]Vincent Dumoulin, Jonathon Shlens and Manjunath Kudlur. "A learned representation for artistic style." arXiv preprint arXiv:1610.07629 (2016).[pdf]★★★★

地址：https://arxiv.org/pdf/1610.00633

█[8]Gatys, Leon and Ecker, et al."Controlling Perceptual Factors in Neural Style Transfer." arXiv preprint arXiv:1611.07865 (2016).[pdf](control style transfer over spatial location,colour information and across spatial scale) ★★★★

地址：https://arxiv.org/pdf/1610.04286.pdf

█[9]Ulyanov, Dmitry and Lebedev, Vadim, et al. "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images." arXiv preprint arXiv:1603.03417(2016).[pdf](纹理生成和风格变化)★★★★

地址：https://arxiv.org/pdf/1611.03673

3.8 目标分割 Object Segmentation

█[1]J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation.” in CVPR, 2015.[pdf]★★★★★

地址：https://arxiv.org/pdf/1411.4038v2.pdf

█[2]L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. "Semantic image segmentation with deep convolutional nets and fully connected crfs." In ICLR, 2015.[pdf]★★★★★

地址：https://arxiv.org/pdf/1606.00915v1.pdf

█[3]Pinheiro, P.O., Collobert, R., Dollar, P. "Learning to segment object candidates." In: NIPS. 2015.[pdf]★★★★

地址：https://arxiv.org/pdf/1506.06204v2.pdf

█[4]Dai, J., He, K., Sun, J. "Instance-aware semantic segmentation via multi-task network cascades." in CVPR. 2016[pdf]★★★

地址：https://arxiv.org/pdf/1512.04412v1.pdf

█[5]Dai, J., He, K., Sun, J. "Instance-sensitive Fully Convolutional Networks." arXiv preprint arXiv:1603.08678 (2016).[pdf]★★★

地址：https://arxiv.org/pdf/1603.08678v1.pdf

原文地址：https://github.com/songrotek/Deep-Learning-Papers-Reading-Roadmap雷锋网获授权获授权

深度学习盛会ICLR2017最佳论文都是啥？，雷锋网带你5min过重点（附论文链接）

深度学习全网最全学习资料汇总之模型介绍篇

深度学习全网最全学习资料汇总之入门篇

深度学习零基础进阶第四弹?｜干货分享

雷锋网版权文章，未经授权禁止转载。详情见转载须知。