Weak Supervision Learning for Object Co-Segmentation

The booming of multimedia technologies has promoted the diversity of visual big data. To learn common features across heterogeneous image data, the image co-processing has exhibited its advantages over the separate one. Recently, an active topic of image co-processing is the object co-segmentation, which aims at simultaneously extracting and segmenting shared objects from relevant images. In this paper, we address this problem with a weak-supervision-based probabilistic model. We introduce the weakly supervised priors to alleviate the confusion between common foreground and background, thereby facilitating performance improvement. To ensure the validity of potential background prior knowledge, the nodes on four sides of image are respectively leveraged as the labelled queries. After that, we develop quantitative probabilistic metrics for precisely measuring internal consistencies within single image and correlations between multiple images. Combining the intra-image consistencies with the inter-image correlations, we propose an optimized energy function coupled with binary labeling and graph connectivity to carry out the object co-segmentation. Extensively experimental results on real-world datasets demonstrate that the proposed method achieves superior co-segmentation performance to the state-of-the-arts, with a significantly reduced time consumption.