NIPS 2017 深度学习论文集锦 (1)
[1] Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning
Zhen He, Shaobing Gao, Liang Xiao,
Daxue Liu, Hangen He, David Barber
https://papers.nips.cc/paper/6606-wider-and-deeper-cheaper-and-faster-tensorized-lstms-for-sequence-learning.pdf
这篇论文主要基于LSTM进行扩展。
网络结构如下
一些类似模型
[2] Deep Subspace Clustering Networks
Pan Ji, Tong Zhang, Hongdong Li,
Mathieu Salzmann, Ian Reid
https://papers.nips.cc/paper/6608-deep-subspace-clustering-networks.pdf
这篇论文主要基于Deep Convolutional Auto-Encoder进行扩展。
网络结构如下
模型的源泉在于下面这个模型
[3] Attentional Pooling for Action Recognition
Rohit Girdhar, Deva Ramanan
https://papers.nips.cc/paper/6609-attentional-pooling-for-action-recognition.pdf
这篇论文主要考虑了注意力模型和卷积神经网络。
网络结构如下
[4] Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis
Jian Zhao, Lin Xiong, Panasonic Karlekar Jayashree, Jianshu Li, Fang Zhao, Zhecan Wang,
Panasonic Sugiri Pranata,
Panasonic Shengmei Shen,
Shuicheng Yan, Jiashi Feng
https://papers.nips.cc/paper/6612-dual-agent-gans-for-photorealistic-and-identity-preserving-profile-face-synthesis.pdf
这篇论文主要对GAN进行扩展。
网络结构如下
[5] Dilated Recurrent Neural Networks
Shiyu Chang, Yang Zhang, Wei Han, Mo Yu, Xiaoxiao Guo, Wei Tan,
Xiaodong Cui, Michael Witbrock,
Mark A. Hasegawa-Johnson,
Thomas S. Huang
https://papers.nips.cc/paper/6613-dilated-recurrent-neural-networks.pdf
这篇论文主要对RNN进行扩展。
网络结构如下
[6] Cortical microcircuits as gated-recurrent neural networks
Rui Costa,
Ioannis Alexandros Assael,
Brendan Shillingford,
Nando de Freitas, TIm Vogels
https://papers.nips.cc/paper/6631-cortical-microcircuits-as-gated-recurrent-neural-networks.pdf
这篇论文主要讨论RNN。
网络结构如下
[7] MaskRNN: Instance Level Video Object Segmentation
Yuan-Ting Hu, Jia-Bin Huang, Alexander Schwing
https://papers.nips.cc/paper/6636-maskrnn-instance-level-video-object-segmentation.pdf
这篇论文主要讨论RNN
模型结构如下
[8] Gated Recurrent Convolution Neural Network for OCR
Jianfeng Wang, Xiaolin Hu
https://papers.nips.cc/paper/6637-gated-recurrent-convolution-neural-network-for-ocr.pdf
这篇论文主要关于RCNN。
网络结构如下
[9] Towards Accurate Binary
Convolutional Neural Network
Xiaofan Lin, Cong Zhao, Wei Pan
https://papers.nips.cc/paper/6638-towards-accurate-binary-convolutional-neural-network.pdf
这篇论文主要对CNN进行扩展。
网络结构如下
[10] Semi-Supervised Learning for Optical Flow with Generative Adversarial
Networks
Wei-Sheng Lai, Jia-Bin Huang,
Ming-Hsuan Yang
https://papers.nips.cc/paper/6639-semi-supervised-learning-for-optical-flow-with-generative-adversarial-networks.pdf
这篇论文主要讨论GAN。
网络结构如下
[11] Preventing Gradient Explosions in Gated Recurrent Units
Sekitoshi Kanai,
Yasuhiro Fujiwara, Sotetsu Iwamura
https://papers.nips.cc/paper/6647-preventing-gradient-explosions-in-gated-recurrent-units.pdf
这篇侧重在理论研究。
[12] f-GANs in an Information Geometric Nutshell
Richard Nock, Zac Cranko, Aditya K. Menon, Lizhen Qu, Robert C. Williamson
https://papers.nips.cc/paper/6649-f-gans-in-an-information-geometric-nutshell.pdf
这篇侧重在理论研究
[13] Learning Spherical Convolution for Fast Features from 360° Imagery
Yu-Chuan Su, Kristen Grauman
https://papers.nips.cc/paper/6656-learning-spherical-convolution-for-fast-features-from-360-imagery.pdf
核心如下
[14] Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks
Nanyang Ye, Zhanxing Zhu, Rafal Mantiuk
https://papers.nips.cc/paper/6664-langevin-dynamics-with-continuous-tempering-for-training-deep-neural-networks.pdf
这篇偏理论研究。
[15] Deep Mean-Shift Priors for Image Restoration
Siavash Arjomand Bigdeli, Matthias Zwicker, Paolo Favaro, Meiguang Jin
效果如下
[16] Introspective Classification with Convolutional Nets
Long Jin, Justin Lazarow, Zhuowen Tu
https://papers.nips.cc/paper/6684-introspective-classification-with-convolutional-nets.pdf
这篇论文主要关于CNN
网络结构如下
[17] Compression-aware Training of Deep Networks
Jose M. Alvarez, Mathieu Salzmann
https://papers.nips.cc/paper/6687-compression-aware-training-of-deep-networks.pdf
这篇偏理论研究。
[18] PredRNN: Recurrent Neural Networks for
Predictive Learning using Spatiotemporal LSTMs
Yunbo Wang, Mingsheng Long, Jianmin Wang, Zhifeng Gao, Philip S. Yu
https://papers.nips.cc/paper/6689-predrnn-recurrent-neural-networks-for-predictive-learning-using-spatiotemporal-lstms.pdf
这篇论文对RNN进行了扩展。
网络结构如下
相关网络结构如下
[19] SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
Kristof Schütt,
Pieter-Jan Kindermans,
Huziel Enoc Sauceda Felix,
Stefan Chmiela,
Alexandre Tkatchenko, Klaus-Robert Müller
https://papers.nips.cc/paper/6700-schnet-a-continuous-filter-convolutional-neural-network-for-modeling-quantum-interactions.pdf
这篇论文对CNN进行了扩展。
网络结构如下
[20] Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
Antti Tarvainen, Harri Valpola
https://papers.nips.cc/paper/6719-mean-teachers-are-better-role-models-weight-averaged-consistency-targets-improve-semi-supervised-deep-learning-results.pdf
网络结构如下
