English

Salient Object Detection via Bounding-box Supervision

Computer Vision and Pattern Recognition 2022-05-12 v1 Machine Learning

Abstract

The success of fully supervised saliency detection models depends on a large number of pixel-wise labeling. In this paper, we work on bounding-box based weakly-supervised saliency detection to relieve the labeling effort. Given the bounding box annotation, we observe that pixels inside the bounding box may contain extensive labeling noise. However, as a large amount of background is excluded, the foreground bounding box region contains a less complex background, making it possible to perform handcrafted features-based saliency detection with only the cropped foreground region. As the conventional handcrafted features are not representative enough, leading to noisy saliency maps, we further introduce structure-aware self-supervised loss to regularize the structure of the prediction. Further, we claim that pixels outside the bounding box should be background, thus partial cross-entropy loss function can be used to accurately localize the accurate background region. Experimental results on six benchmark RGB saliency datasets illustrate the effectiveness of our model.

Keywords

Cite

@article{arxiv.2205.05245,
  title  = {Salient Object Detection via Bounding-box Supervision},
  author = {Mengqi He and Jing Zhang and Wenxin Yu},
  journal= {arXiv preprint arXiv:2205.05245},
  year   = {2022}
}

Comments

5 pages,4 figures,submitted to ICIP 2022

R2 v1 2026-06-24T11:13:47.861Z