Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2021 | Annual Conference on Neural Information Processing Systems | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peiyu Yu | 1 | 0 | 0.68 |
Sirui Xie | 2 | 0 | 1.35 |
Xiaojian Ma | 3 | 1 | 1.37 |
Yixin Zhu | 4 | 0 | 0.34 |
Ying Nian Wu | 5 | 1652 | 267.72 |
Song-Chun Zhu | 6 | 0 | 0.34 |