开发者社区> 玄学酱> 正文

126篇殿堂级深度学习论文分类整理 从入门到应用 | 干货

简介:
+关注继续查看

126篇殿堂级深度学习论文分类整理 从入门到应用 | 干货

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(公众号: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, Haşim, 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 Salakhutdinov. "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 Rothörl, 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 







本文作者:三川
本文转自雷锋网禁止二次转载,原文链接

版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。

相关文章
深度学习模型实战-深度学习模型在各大公司实际生产环境的应用讲解文章
建这个仓库的是因为工作之后发现生产环境中应用的模型需要做到速度和效果的平衡,并不是越复杂越好。所以一味的追求新的模型效果不大(并不是不追,也要多看新东西)。学到模型最终是要用,而且要用好,于是就建了这么个仓库,积累一下深度学习模型在各个公司中的应用以及细节,这样在自己工作中可以做到借鉴。主要是罗列一些各大公司分享的文章,涉及到搜索/推荐/自然语言处理(NLP),持续更新... 仓库地址:https://github.com/DA-southampton/Tech_Aarticle/edit/master/README.md
5 0
【转】听说你了解深度学习最常用的学习算法:Adam优化算法?
深度学习常常需要大量的时间和机算资源进行训练,这也是困扰深度学习算法开发的重大原因。虽然我们可以采用分布式并行训练加速模型的学习,但所需的计算资源并没有丝毫减少。而唯有需要资源更少、令模型收敛更快的最优化算法,才能从根本上加速机器的学习速度和效果,Adam 算法正为此而生!
10 0
内容推荐场景中自监督学习的应用
内容推荐场景中自监督学习的应用
5 0
10行Python代码能做出哪些有趣的事情?
Python 凭借语法的易学性,代码的简洁性以及类库的丰富性,赢得了众多开发者的喜爱。下面我们来看看,用不超过10行代码能实现些什么有趣的功能
15 0
深度粗排在天猫新品中的实践
深度粗排在天猫新品中的实践
7 0
使用 Python 实现一个简单的智能聊天机器人
使用 Python 实现一个简单的智能聊天机器人
11 0
最好用的 8 款 React Datepicker 时间日期选择器测评推荐
React 时间日期选择器(date-timepicker)组件,与表单、富文本、表格、拖拽等组件一样,是大家用 React 搭建项目时使用最频繁的组件之一。React DateTimePicker 除了基础选择日期时间外,还有非常多样的功能配合不同场景使用,比如 12/24小时,禁止选择某些日期,高亮某些日期,夜间模式,多语言,酒店订单的特别场景等。本文记录了我自己使用多年最好用的 8 款 React DateTimePicker 组件,每一款都经过我实际测试,推荐给大家。
12 0
整理了25个Python文本处理案例,收藏!
Python 处理文本是一项非常常见的功能,本文整理了多种文本提取及NLP相关的案例,还是非常用心的 文章很长,高低要忍一下,如果忍不了,那就收藏吧,总会用到的
7 0
※【python自学】7个Python生态系统核心库,你值得拥有
※【python自学】7个Python生态系统核心库,你值得拥有
10 0
新手小白成功部署web项目在阿里云服务器
新手小白成功部署web项目在阿里云服务器,感谢阿里云的免费云服务器,能让我独立搭建自己的服务器,搭载自己的web项目
18 0
+关注
玄学酱
这个时候,玄酱是不是应该说点什么...
20709
文章
438
问答
来源圈子
更多
+ 订阅
文章排行榜
最热
最新
相关电子书
更多
OceanBase 入门到实战教程
立即下载
阿里云图数据库GDB,加速开启“图智”未来.ppt
立即下载
实时数仓Hologres技术实战一本通2.0版(下)
立即下载