Timezone: »

 
Poster
Unsupervised Foreground Extraction via Deep Region Competition
Peiyu Yu · Sirui Xie · Xiaojian (Shawn) Ma · Yixin Zhu · Ying Nian Wu · Song-Chun Zhu

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @
in Poster Session 2 »

We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. Foreground extraction can be viewed as a special case of generic image segmentation that focuses on identifying and disentangling objects from the background. In this work, we rethink the foreground extraction by reconciling energy-based prior with generative image modeling in the form of Mixture of Experts (MoE), where we further introduce the learned pixel re-assignment as the essential inductive bias to capture the regularities of background regions. With this modeling, the foreground-background partition can be naturally found through Expectation-Maximization (EM). We show that the proposed method effectively exploits the interaction between the mixture components during the partitioning process, which closely connects to region competition, a seminal approach for generic image segmentation. Experiments demonstrate that DRC exhibits more competitive performances on complex real-world data and challenging multi-object scenes compared with prior methods. Moreover, we show empirically that DRC can potentially generalize to novel foreground objects even from categories unseen during training.

Keywords: Self-Supervised Learning · Generative Model

Author Information

Peiyu Yu (UCLA)
Sirui Xie (UCLA)
Xiaojian (Shawn) Ma (University of California, Los Angeles)
Yixin Zhu (University of California, Los Angeles)
Ying Nian Wu (University of California, Los Angeles)
Song-Chun Zhu (UCLA)

More from the Same Authors