Comprehensive Saliency Fusion for Object Co-segmentation
This work addresses object co-segmentation for computer vision applications, but it appears incremental as it builds on existing saliency fusion ideas with deep learning enhancements.
The paper tackles object co-segmentation by proposing a comprehensive saliency fusion method that combines saliency maps from both the same and different images, using deep learning for extraction and correspondence. It achieves much-improved results on benchmark datasets like iCoseg, MSRC, and Internet Images, though no specific numbers are provided.
Object co-segmentation has drawn significant attention in recent years, thanks to its clarity on the expected foreground, the shared object in a group of images. Saliency fusion has been one of the promising ways to carry it out. However, prior works either fuse saliency maps of the same image or saliency maps of different images to extract the expected foregrounds. Also, they rely on hand-crafted saliency extraction and correspondence processes in most cases. This paper revisits the problem and proposes fusing saliency maps of both the same image and different images. It also leverages advances in deep learning for the saliency extraction and correspondence processes. Hence, we call it comprehensive saliency fusion. Our experiments reveal that our approach achieves much-improved object co-segmentation results compared to prior works on important benchmark datasets such as iCoseg, MSRC, and Internet Images.