(转) Awesome - Most Cited Deep Learning Papers

时间：2023-04-25 20:18:38

转自：https://github.com/terryum/awesome-deep-learning-papers

Awesome - Most Cited Deep Learning Papers

(转) Awesome - Most Cited Deep Learning Papers

A curated list of the most cited deep learning papers (since 2010)

I believe that there exist classic deep learning papers which are worth reading regardless of their application areas. Rather than providing overwhelming amount of papers, I would like to provide a curated list of the classic deep learning papers which can be considered as must-reads in some research areas.

Awesome list criteria

  • < 6 months : Please refer to New papers worth reading section
  • < 1 year : +30 citations
  • 2016 : +50 citations (✨ +80)
  • 2015 : +100 citations (✨ +200)
  • 2014 : +200 citations (✨ +400)
  • 2013 : +300 citations (✨ +600)
  • 2012 : +400 citations (✨ +800)
  • Before 2012 : Please refer to Classic papers section

I need your contributions! Please read the contributing guide before you make a pull request.

Table of Contents

Total 85 papers except for the papers in Hardware / Software, Papers Worth Reading, and Classic Papers sections.

Survey / Review

  • Deep learning (Book, 2016), Goodfellow et al. (Bengio) [html]
  • Deep learning (2015), Y. LeCun, Y. Bengio and G. Hinton [pdf] ✨
  • Deep learning in neural networks: An overview (2015), J. Schmidhuber [pdf] ✨
  • Representation learning: A review and new perspectives (2013), Y. Bengio et al. [pdf] ✨

Theory / Distillation

  • Distilling the knowledge in a neural network (2015), G. Hinton et al. (Hinton, Vinyals, Dean: Google) [pdf] ✨
  • Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (2015), A. Nguyen et al. [pdf]
  • How transferable are features in deep neural networks? (2014), J. Yosinski et al. (Bengio) [pdf]
  • Return of the devil in the details: delving deep into convolutional nets (2014), K. Chatfield et al. [pdf] ✨
  • Why does unsupervised pre-training help deep learning (2010), D. Erhan et al. (Bengio) [pdf]
  • Understanding the difficulty of training deep feedforward neural networks (2010), X. Glorot and Y. Bengio [pdf]

Optimization / Regularization

  • Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015), S. Loffe and C. Szegedy (Google) [pdf] ✨
  • Delving deep into rectifiers: Surpassing human-level performance on imagenet classification (2015), K. He et al. (He) [pdf]✨
  • Recurrent neural network regularization (2014), W. Zaremba et al. (Sutskever, Vinyals: Google) [pdf]
  • Dropout: A simple way to prevent neural networks from overfitting (2014), N. Srivastava et al. (Hinton) [pdf] ✨
  • Adam: A method for stochastic optimization (2014), D. Kingma and J. Ba [pdf]
  • Spatial pyramid pooling in deep convolutional networks for visual recognition (2014), K. He et al. [pdf] ✨
  • On the importance of initialization and momentum in deep learning (2013), I. Sutskever et al. (Hinton) [pdf]
  • Regularization of neural networks using dropconnect (2013), L. Wan et al. (LeCun) [pdf]
  • Improving neural networks by preventing co-adaptation of feature detectors (2012), G. Hinton et al. [pdf] ✨
  • Random search for hyper-parameter optimization (2012) J. Bergstra and Y. Bengio [pdf]

Network Models

  • Inception-v4, inception-resnet and the impact of residual connections on learning (2016), C. Szegedy et al. (Google) [pdf]
  • Identity Mappings in Deep Residual Networks (2016), K. He et al. (He) [pdf]
  • Deep residual learning for image recognition (2016), K. He et al. (He) [pdf] ✨
  • Region-based convolutional networks for accurate object detection and segmentation (2016), R. Girshick et al. (He) [pdf]
  • Going deeper with convolutions (2015), C. Szegedy et al. (Google) [pdf] ✨
  • Fast R-CNN (2015), R. Girshick (He) [pdf] ✨
  • An Empirical Exploration of Recurrent Network Architectures (2015), R. Jozefowicz et al. Sutskever: Google [pdf]
  • Fully convolutional networks for semantic segmentation (2015), J. Long et al. [pdf] ✨
  • Very deep convolutional networks for large-scale image recognition (2014), K. Simonyan and A. Zisserman [pdf] ✨
  • OverFeat: Integrated recognition, localization and detection using convolutional networks (2014), P. Sermanet et al. (LeCun) [pdf]
  • Visualizing and understanding convolutional networks (2014), M. Zeiler and R. Fergus [pdf] ✨
  • Maxout networks (2013), I. Goodfellow et al. (Bengio) [pdf]
  • Network in network (2013), M. Lin et al. [pdf]
  • ImageNet classification with deep convolutional neural networks (2012), A. Krizhevsky et al. (Hinton) [pdf] ✨
  • Large scale distributed deep networks (2012), J. Dean et al. [pdf] ✨
  • Deep sparse rectifier neural networks (2011), X. Glorot et al. (Bengio) [pdf]

Unsupervised / Adversarial

  • Unsupervised representation learning with deep convolutional generative adversarial networks (2015), A. Radford et al. [pdf]
  • CNN features off-the-Shelf: An astounding baseline for recognition (2014), A. Razavian et al. [pdf] ✨
  • Generative adversarial nets (2014), I. Goodfellow et al. (Bengio) [pdf]
  • Intriguing properties of neural networks (2014), C. Szegedy et al. (Sutskever, Goodfellow: Google) [pdf]
  • Auto-encoding variational Bayes (2013), D. Kingma and M. Welling [pdf]
  • Building high-level features using large scale unsupervised learning (2013), Q. Le et al. [pdf] ✨
  • An analysis of single-layer networks in unsupervised feature learning (2011), A. Coates et al. [pdf]
  • Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion (2010), P. Vincent et al. (Bengio) [pdf]
  • A practical guide to training restricted boltzmann machines (2010), G. Hinton [pdf]

Image

  • Image Super-Resolution Using Deep Convolutional Networks (2016), C. Dong et al. (He) [pdf] ✨
  • Reading text in the wild with convolutional neural networks (2016), M. Jaderberg et al. (DeepMind) [pdf]
  • Learning Deconvolution Network for Semantic Segmentation (2015), H. Noh et al. [pdf]
  • Imagenet large scale visual recognition challenge (2015), O. Russakovsky et al. [pdf] ✨
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015), S. Ren et al. [pdf] ✨
  • DRAW: A recurrent neural network for image generation (2015), K. Gregor et al. [pdf]
  • Scalable object detection using deep neural networks (2014), D. Erhan et al. (Google) [pdf]
  • Learning a Deep Convolutional Network for Image Super-Resolution (2014, C. Dong et al. (He) [pdf]
  • Rich feature hierarchies for accurate object detection and semantic segmentation (2014), R. Girshick et al. [pdf] ✨
  • Learning a Deep Convolutional Network for Image Super-Resolution (2014), C. Dong et al. [pdf]
  • Learning and transferring mid-Level image representations using convolutional neural networks (2014), M. Oquab et al. [pdf]
  • DeepFace: Closing the Gap to Human-Level Performance in Face Verification (2014), Y. Taigman et al. (Facebook) [pdf] ✨
  • Decaf: A deep convolutional activation feature for generic visual recognition (2013), J. Donahue et al. [pdf] ✨
  • Learning hierarchical features for scene labeling (2013), C. Farabet et al. (LeCun) [pdf]
  • Learning mid-level features for recognition (2010), Y. Boureau (LeCun) [pdf]

Caption / Visual QnA

  • VQA: Visual question answering (2015), S. Antol et al. [pdf]
  • Towards ai-complete question answering: A set of prerequisite toy tasks (2015), J. Weston et al. (Mikolov: Facebook) [pdf]
  • Ask me anything: Dynamic memory networks for natural language processing (2015), A. Kumar et al. [pdf]
  • A large annotated corpus for learning natural language inference (2015), S. Bowman et al. [pdf]
  • Show, attend and tell: Neural image caption generation with visual attention (2015), K. Xu et al. (Bengio) [pdf] ✨
  • Show and tell: A neural image caption generator (2015), O. Vinyals et al. (Vinyals: Google) [pdf] ✨
  • Long-term recurrent convolutional networks for visual recognition and description (2015), J. Donahue et al. [pdf] ✨
  • Deep visual-semantic alignments for generating image descriptions (2015), A. Karpathy and L. Fei-Fei [pdf] ✨

Video / Human Activity

  • Beyond short snippents: Deep networks for video classification (2015) (Vinyals: Google) [pdf] ✨
  • Large-scale video classification with convolutional neural networks (2014), A. Karpathy et al. (FeiFei) [pdf] ✨
  • DeepPose: Human pose estimation via deep neural networks (2014), A. Toshev and C. Szegedy (Google) [pdf]
  • Two-stream convolutional networks for action recognition in videos (2014), K. Simonyan et al. [pdf]
  • A survey on human activity recognition using wearable sensors (2013), O. Lara and M. Labrador [pdf]
  • 3D convolutional neural networks for human action recognition (2013), S. Ji et al. [pdf]
  • Action recognition with improved trajectories (2013), H. Wang and C. Schmid [pdf]
  • Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis (2011), Q. Le et al. [pdf]

Word Embedding

  • Glove: Global vectors for word representation (2014), J. Pennington et al. [pdf] ✨
  • Distributed representations of sentences and documents (2014), Q. Le and T. Mikolov (Le, Mikolov: Google) [pdf] (Google)✨
  • Distributed representations of words and phrases and their compositionality (2013), T. Mikolov et al. (Google) [pdf] ✨
  • Efficient estimation of word representations in vector space (2013), T. Mikolov et al. (Google) [pdf] ✨
  • Devise: A deep visual-semantic embedding model (2013), A. Frome et al., (Mikolov: Google) [pdf]
  • Word representations: a simple and general method for semi-supervised learning (2010), J. Turian (Bengio) [pdf]

Machine Translation / QnA

  • Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016), Y. Wu et al. (Le, Vinyals, Dean: Google) [pdf]
  • Exploring the limits of language modeling (2016), R. Jozefowicz et al. (Vinyals: DeepMind) [pdf]
  • A neural conversational model, O. Vinyals and Q. Le. (Vinyals, Le: Google) [pdf]
  • Grammar as a foreign language (2015), O. Vinyals et al. (Vinyals, Sutskever, Hinton: Google) [pdf]
  • Towards ai-complete question answering: A set of prerequisite toy tasks (2015), J. Weston et al. [pdf]
  • Neural machine translation by jointly learning to align and translate (2014), D. Bahdanau et al. (Bengio) [pdf] ✨
  • Sequence to sequence learning with neural networks (2014), I. Sutskever et al. (Sutskever, Vinyals, Le: Google) [pdf] ✨
  • Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014), K. Cho et al. (Bengio) [pdf]
  • A convolutional neural network for modelling sentences (2014), N. Kalchbrenner et al. [pdf]
  • Convolutional neural networks for sentence classification (2014), Y. Kim [pdf]
  • The stanford coreNLP natural language processing toolkit (2014), C. Manning et al. [pdf] ✨
  • Recursive deep models for semantic compositionality over a sentiment treebank (2013), R. Socher et al. [pdf] ✨
  • Linguistic Regularities in Continuous Space Word Representations (2013), T. Mikolov et al. (Mikolov: Microsoft) [pdf]
  • Natural language processing (almost) from scratch (2011), R. Collobert et al. [pdf] ✨
  • Recurrent neural network based language model (2010), T. Mikolov et al. [pdf]

Speech / Etc.

  • Automatic speech recognition - A deep learning approach (Book, 2015), D. Yu and L. Deng (Microsoft) [html]
  • Speech recognition with deep recurrent neural networks (2013), A. Graves (Hinton) [pdf]
  • Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups (2012), G. Hinton et al. [pdf] ✨
  • Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition (2012) G. Dahl et al. [pdf]✨
  • Acoustic modeling using deep belief networks (2012), A. Mohamed et al. (Hinton) [pdf]

RL / Robotics

  • Mastering the game of Go with deep neural networks and tree search (2016), D. Silver et al. (Sutskever: DeepMind) [pdf]✨
  • Human-level control through deep reinforcement learning (2015), V. Mnih et al. (DeepMind) [pdf] ✨
  • Deep learning for detecting robotic grasps (2015), I. Lenz et al. [pdf]
  • Playing atari with deep reinforcement learning (2013), V. Mnih et al. (DeepMind) [pdf])

Hardware / Software

  • TensorFlow: Large-scale machine learning on heterogeneous distributed systems (2016), M. Abadi et al. (Google) [pdf] ✨
  • Theano: A Python framework for fast computation of mathematical expressions, R. Al-Rfou et al. (Bengio)
  • MatConvNet: Convolutional neural networks for matlab (2015), A. Vedaldi and K. Lenc [pdf]
  • Caffe: Convolutional architecture for fast feature embedding (2014), Y. Jia et al. [pdf] ✨

Papers Worth Reading

Newly released papers which do not meet the criteria but worth reading

  • WaveNet: A Generative Model for Raw Audio (2016), A. Oord et al. (DeepMind) [pdf] [web]
  • Layer Normalization (2016), J. Ba et al. (Hinton) [pdf]
  • Deep neural network architectures for deep reinforcement learning, Z. Wang et al. (DeepMind) [pdf]
  • Learning to learn by gradient descent by gradient descent (2016), M. Andrychowicz et al. (DeepMind) [pdf]
  • Adversarially learned inference (2016), V. Dumoulin et al. [web][pdf]
  • Understanding convolutional neural networks (2016), J. Koushik [pdf]
  • SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size (2016), F. Iandola et al. [pdf]
  • Learning to compose neural networks for question answering (2016), J. Andreas et al. [pdf]
  • Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection (2016) (Google), S. Levine et al. [pdf]
  • Taking the human out of the loop: A review of bayesian optimization (2016), B. Shahriari et al. [pdf]
  • Eie: Efficient inference engine on compressed deep neural network (2016), S. Han et al. [pdf]
  • Adaptive Computation Time for Recurrent Neural Networks (2016), A. Graves [pdf]
  • Pixel recurrent neural networks (2016), A. van den Oord et al. (DeepMind) [pdf]
  • Densely connected convolutional networks (2016), G. Huang et al. [pdf]

Classic Papers

Classic papers (1997~2011) which cause the advent of deep learning era

  • Recurrent neural network based language model (2010), T. Mikolov et al. [pdf]
  • Learning deep architectures for AI (2009), Y. Bengio. [pdf]
  • Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations (2009), H. Lee et al. [pdf]

  • Greedy layer-wise training of deep networks (2007), Y. Bengio et al. [pdf]

  • Reducing the dimensionality of data with neural networks, G. Hinton and R. Salakhutdinov. [pdf]

  • A fast learning algorithm for deep belief nets (2006), G. Hinton et al. [pdf]
  • Gradient-based learning applied to document recognition (1998), Y. LeCun et al. [pdf]
  • Long short-term memory (1997), S. Hochreiter and J. Schmidhuber. [pdf]

Distinguished Researchers

Distinguished deep learning researchers who have published +3 (✨ +6) papers on the awesome list (The papers in Hardware / Software, Papers Worth Reading, Classic Papers sections are excluded in counting.)

Acknowledgement

Thank you for all your contributions. Please make sure to read the contributing guide before you make a pull request.

You can follow my facebook page or google plus to get useful information about machine learning and robotics. If you want to have a talk with me, please send me a message to my facebook page.

You can also check out my blog where I share my thoughts on my research area (deep learning for human/robot motions). I got some thoughts while making this list and summerized them in a blog post, "Some trends of recent deep learning researches".

License

(转) Awesome - Most Cited Deep Learning Papers

To the extent possible under law, Terry T. Um has waived all copyright and related or neighboring rights to this work.

相关文章