【论文推荐】最新五篇生成对抗网络相关论文—异构推理、姿态归一化图像生成、权重共享、对抗泛化方法、深层语义哈希、高分辨率深度卷积

2018 年 5 月 16 日 专知专知内容组

【导读】专知内容组前两天为大家推荐了十六篇生成对抗网络（Generative Adversarial Networks ）相关文章，今天又整理了最近五篇生成对抗网络相关文章，为大家进行介绍，欢迎查看!

17.Generative Model for Heterogeneous Inference（异构推理的生成模型）

作者：Honggang Zhou,Yunchun Li,Hailong Yang,Wei Li,Jie Jia

机构：Beihang University，Taiyuan University of Technology

摘要：Generative models (GMs) such as Generative Adversary Network (GAN) and Variational Auto-Encoder (VAE) have thrived these years and achieved high quality results in generating new samples. Especially in Computer Vision, GMs have been used in image inpainting, denoising and completion, which can be treated as the inference from observed pixels to corrupted pixels. However, images are hierarchically structured which are quite different from many real-world inference scenarios with non-hierarchical features. These inference scenarios contain heterogeneous stochastic variables and irregular mutual dependences. Traditionally they are modeled by Bayesian Network (BN). However, the learning and inference of BN model are NP-hard thus the number of stochastic variables in BN is highly constrained. In this paper, we adapt typical GMs to enable heterogeneous learning and inference in polynomial time.We also propose an extended autoregressive (EAR) model and an EAR with adversary loss (EARA) model and give theoretical results on their effectiveness. Experiments on several BN datasets show that our proposed EAR model achieves the best performance in most cases compared to other GMs. Except for black box analysis, we've also done a serial of experiments on Markov border inference of GMs for white box analysis and give theoretical results.

期刊：arXiv, 2018年4月26日

网址：

http://www.zhuanzhi.ai/document/e2b18fb5b9dea86897b6943fefaa6c5b

18.Pose-Normalized Image Generation for Person Re-identification（用于行人重识别的姿态归一化图像生成）

作者：Xuelin Qian,Yanwei Fu,Tao Xiang,Wenxuan Wang,Jie Qiu,Yang Wu,Yu-Gang Jiang,Xiangyang Xue

机构：Queen Mary University of London，Fudan University

摘要：Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on the pose. The model is based on a generative adversarial network (GAN) designed specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). With the synthesized images, we can learn a new type of deep re-id feature free of the influence of pose variations. We show that this feature is strong on its own and complementary to features learned with the original images. Importantly, under the transfer learning setting, we show that our model generalizes well to any new re-id dataset without the need for collecting any training data for model fine-tuning. The model thus has the potential to make re-id model truly scalable.

期刊：arXiv, 2018年4月25日

网址：

http://www.zhuanzhi.ai/document/b9ca0e4a09c5abeda669e954f22304b2

19.Unsupervised Neural Machine Translation with Weight Sharing（权重共享的无监督神经机器翻译）

作者：Zhen Yang,Wei Chen,Feng Wang,Bo Xu

机构：University of Chinese Academy of Sciences

摘要：Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data. The models proposed for unsupervised NMT often use only one shared encoder to map the pairs of sentences from different languages to a shared-latent space, which is weak in keeping the unique and internal characteristics of each language, such as the style, terminology, and sentence structure. To address this issue, we introduce an extension by utilizing two independent encoders but sharing some partial weights which are responsible for extracting high-level representations of the input sentences. Besides, two different generative adversarial networks (GANs), namely the local GAN and global GAN, are proposed to enhance the cross-language translation. With this new approach, we achieve significant improvements on English-German, English-French and Chinese-to-English translation tasks.

期刊：arXiv, 2018年4月24日

网址：

http://www.zhuanzhi.ai/document/d8155e035fcb62f192b632d5df9385cc

20.Adversarial Generalized Method of Moments

作者：Greg Lewis,Vasilis Syrgkanis

摘要：We provide an approach for learning deep neural net representations of models described via conditional moment restrictions. Conditional moment restrictions are widely used, as they are the language by which social scientists describe the assumptions they make to enable causal inference. We formulate the problem of estimating the underling model as a zero-sum game between a modeler and an adversary and apply adversarial training. Our approach is similar in nature to Generative Adversarial Networks (GAN), though here the modeler is learning a representation of a function that satisfies a continuum of moment conditions and the adversary is identifying violating moments. We outline ways of constructing effective adversaries in practice, including kernels centered by k-means clustering, and random forests. We examine the practical performance of our approach in the setting of non-parametric instrumental variable regression.

期刊：arXiv, 2018年4月24日

网址：

http://www.zhuanzhi.ai/document/581abce80556cd3a3c18f982c201a5e1

21.Deep Semantic Hashing with Generative Adversarial Networks（基于生成对抗网络的深层语义哈希）

作者：Zhaofan Qiu,Yingwei Pan,Ting Yao,Tao Mei

SIGIR 2017 Oral

机构：University of Science and Technology of China

摘要：Hashing has been a widely-adopted technique for nearest neighbor search in large-scale image retrieval tasks. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, the cost of annotating data is often an obstacle when applying supervised hashing to a new domain. Moreover, the results can suffer from the robustness problem as the data at training and test stage could come from similar but different distributions. This paper studies the exploration of generating synthetic data through semi-supervised generative adversarial networks (GANs), which leverages largely unlabeled and limited labeled training data to produce highly compelling data with intrinsic invariance and global coherence, for better understanding statistical structures of natural data. We demonstrate that the above two limitations can be well mitigated by applying the synthetic data for hashing. Specifically, a novel deep semantic hashing with GANs (DSH-GANs) is presented, which mainly consists of four components: a deep convolution neural networks (CNN) for learning image representations, an adversary stream to distinguish synthetic images from real ones, a hash stream for encoding image representations to hash codes and a classification stream. The whole architecture is trained end-to-end by jointly optimizing three losses, i.e., adversarial loss to correct label of synthetic or real for each sample, triplet ranking loss to preserve the relative similarity ordering in the input real-synthetic triplets and classification loss to classify each sample accurately. Extensive experiments conducted on both CIFAR-10 and NUS-WIDE image benchmarks validate the capability of exploiting synthetic images for hashing. Our framework also achieves superior results when compared to state-of-the-art deep hash models.

期刊：arXiv, 2018年4月23日

网址：

http://www.zhuanzhi.ai/document/34cb489c4d3fd24d82ea2658774ab214

22.High-Resolution Deep Convolutional Generative Adversarial Networks（高分辨率深度卷积生成对抗网络）

作者：Joachim D. Curtó,Irene C. Zarza,Fernando De La Torre,Irwin King,Michael R. Lyu

机构：City University of Hong Kong，The Chinese University of Hong Kong

摘要：Generative Adversarial Networks (GANs) convergence in a high-resolution setting with a computational constrain of GPU memory capacity (from 12GB to 24 GB) has been beset with difficulty due to the known lack of convergence rate stability. In order to boost network convergence of DCGAN (Deep Convolutional Generative Adversarial Networks) and achieve good-looking high-resolution results we propose a new layered network structure, HDCGAN, that incorporates current state-of-the-art techniques for this effect. A novel dataset, Curt\'o Zarza (CZ), containing human faces from different ethnical groups in a wide variety of illumination conditions and image resolutions is introduced. CZ is enhanced with HDCGAN synthetic images, thus being the first GAN augmented face dataset. We conduct extensive experiments on CelebA and CZ.