Self-supervised co-salient object detection via feature correspondence at multiple scales

arXiv:2403.11107v1 Announce Type: new
Abstract: Our paper introduces a novel two-stage self-supervised approach for detecting co-occurring salient objects (CoSOD) in image groups without requiring segmentation annotations. Unlike existing unsupervised methods that rely solely on patch-level information (e.g. clustering patch descriptors) or on computation heavy off-the-shelf components for CoSOD, our lightweight model leverages feature correspondences at both patch and region levels, significantly improving prediction performance. In the first stage, we train a self-supervised network that detects co-salient regions by computing local …

abstract annotations arxiv clustering components computation cs.cv detection feature image information multiple novel object objects paper segmentation stage type unsupervised via