.png){kind=icon}
返回
Investigating object compositionality in Generative Adversarial Networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2020.07.007.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several core inductive biases. However, a bias to account for the compositional way in which humans structure a visual scene in terms of objects has frequently been overlooked. In this work, we investigate object compositionality as an inductive bias for Generative Adversarial Networks (GANs). We present a minimal modification of a standard generator to incorporate this inductive bias and find that it reliably learns to generate images as compositions of objects. Using this general design as a backbone, we then propose two useful extensions to incorporate dependencies among objects and background. We extensively evaluate our approach on several multi-object image datasets and highlight the merits of incorporating structure for representation learning purposes. In particular, we find that our structured GANs are better at generating multi-object images that are more faithful to the reference distribution. More so, we demonstrate how, by leveraging the structure of the learned generative process, one can 'invert' the learned generative model to perform unsupervised instance segmentation. On the challenging CLEVR dataset, it is shown how our approach is able to improve over other recent purely unsupervised object-centric approaches to image generation. (C) 2020 Elsevier Ltd. All rights reserved.
Keyword:
Generative Adversarial Networks
Objects
Compositionality
Generative modeling
Instance segmentation
Representation learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Generative Adversarial Networks are special cases of Artificial Curiosity (1990) and also closely related to Predictability Minimization (1991)NEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏
查看更多内容