Timezone: »

ComGAN: Unsupervised Disentanglement and Segmentation via Image Composition
Rui Ding · Kehua Guo · Xiangyuan Zhu · Zheng Wu · Liwei Wang

Tue Dec 06 05:00 PM -- 07:00 PM (PST) @

We propose ComGAN, a simple unsupervised generative model, which simultaneously generates realistic images and high semantic masks under an adversarial loss and a binary regularization. In this paper, we first investigate two kinds of trivial solutions in the compositional generation process, and demonstrate their source is vanishing gradients on the mask. Then, we solve trivial solutions from the perspective of architecture. Furthermore, we redesign two fully unsupervised modules based on ComGAN (DS-ComGAN), where the disentanglement module associates the foreground, background and mask with three independent variables, and the segmentation module learns object segmentation. Experimental results show that (i) ComGAN's network architecture effectively avoids trivial solutions without any supervised information and regularization; (ii) DS-ComGAN achieves remarkable results and outperforms existing semi-supervised and weakly supervised methods by a large margin in both the image disentanglement and unsupervised segmentation tasks. It implies that the redesign of ComGAN is a possible direction for future unsupervised work.

Author Information

Rui Ding (Central South University)
Kehua Guo (Central South University, China)
Xiangyuan Zhu (Central South University, China)
Zheng Wu
Liwei Wang (Central South University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2022 Spotlight: Lightning Talks 2B-2 »
    Chenjian Gao · Rui Ding · Lingzhi LI · Fan Yang · Xingting Yao · Jianxin Li · Bing Su · Zhen Shen · Tongda Xu · Shuai Zhang · Ji-Rong Wen · Lin Guo · Fanrong Li · Kehua Guo · Zhongshu Wang · Zhi Chen · Xiangyuan Zhu · Zitao Mo · Dailan He · Hui Xiong · Yan Wang · Zheng Wu · Wenbing Tao · Jian Cheng · Haoyi Zhou · Li Shen · Ping Tan · Liwei Wang · Hongwei Qin