/Deep-Learning-Papers

A document of papers I've read and categorization of them

Deep-Learning-Papers

A document of papers I've read and categorization of them

Contents

Generative Adversarial Nets (GANs)

  • Generative Adversarial Nets [pdf]
    • Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua. NIPS'14
  • Conditional generative adversarial nets [pdf]
    • Mirza, Mehdi and Osindero, Simon. arXiv 1411
  • Energy-Based Generative Adversarial Networks [pdf]
    • Junbo Zhao, Michael Mathieu, Yann LeCun. arXiv 1609
  • InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets [pdf]
    • Chen, Xi and Duan, Yan and Houthooft, Rein and Schulman, John and Sutskever, Ilya and Abbeel, Pieter. NIPS'16
  • Learning to Discover Cross-Domain Relations with Generative Adversarial Networks [pdf]
    • Kim, Taeksoo and Cha, Moonsu and Kim, Hyunsoo and Lee, Jungkwon and Kim, Jiwon. arXiv 1703
  • Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks [pdf]
    • Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A. arXiv 1703

Autoencoders

Adversarial Autoencoders and Its Extensions

  • Adversarial Autoencoders [pdf]
    • Makhzani, Alireza and Shlens, Jonathon and Jaitly, Navdeep and Goodfellow, Ian and Frey, Brendan. arXiv 1511

Variational Autoencoders and Its Extensions

  • Neural discrete representation learning [pdf]
    • van den Oord, Aaron and Vinyals, Oriol and others. NIPS'17
  • Autoencoding Beyond Pixels Using a Learned Similarity Metric [pdf]
    • Larsen, Anders Boesen Lindbo and S{\o}nderby, S{\o}ren Kaae and Larochelle, Hugo and Winther, Ole. arXiv 1512

Theory

  • 谷歌工程師：聊一聊深度學習的weight initialization [link]

Evidence Lower Bound (ELBO)

  • Elbo Surgery: yet Another Way to Carve Up The Variational Evidence Lower Bound [pdf]
    • Hoffman, Matthew D and Johnson, Matthew J. NIPS Workshop'16

APSIPA-related

  • Generative Probabilistic Novelty Detection with Adversarial Autoencoders [[pdf]](Generative Probabilistic Novelty Detection with Adversarial Autoencoders)
    • Stanislav Pidhorskyi · Ranya Almohsen · Gianfranco Doretto. NIPS'19

TO-DO

  • Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
  • Spectral Normalization for Generative Adversarial Networks
  • self-attention GAN
  • Learn To Pay Attention [pdf]
    • Saumya Jetley, Nicholas A. Lord, Namhoon Lee, Philip H.S. Torr. ICLR'18
  • Non-local Neural Networks [pdf]
    • Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He. arXiv'17
  • Structured Attention Networks [pdf]
    • Yoon Kim, Carl Denton, Luong Hoang, Alexander M. Rush. ICLR'17
  • Benchmarking Neural Network Robustness to Common Corruptions and Perturbations [pdf]
  • Large Scale GAN Training for High Fidelity Natural Image Synthesis [pdf]
  • Generating High Fidelity Images With Subscale Pixel Networks and Multidimensional Upscaling [pdf]
  • Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow [pdf]
  • Temporal Difference Variational Auto-Encoder [pdf]
  • Towards Robust, Locally Linear Deep Networks [pdf]
  • Learning Robust Representations by Projecting Superficial Statistics Out [pdf]
  • On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data [pdf]
  • Visualizing and Understanding Generative Adversarial Networks [pdf]
  • Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer [pdf]
  • Approximability of Discriminators Implies Diversity in GANs [pdf]
  • An analytic theory of generalization dynamics and transfer learning in deep linear networks [pdf]
  • Unsupervised Domain Adaptation for Distance Metric Learning [pdf]
  • Lagging Inference Networks and Posterior Collapse in Variational Autoencoders [pdf]