Back to Search
Start Over
Gradient-Induced Co-Saliency Detection
- Publication Year :
- 2020
- Publisher :
- arXiv, 2020.
-
Abstract
- Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images. In this paper, inspired by human behavior, we propose a gradient-induced co-saliency detection (GICD) method. We first abstract a consensus representation for the grouped images in the embedding space; then, by comparing the single image with consensus representation, we utilize the feedback gradient information to induce more attention to the discriminative co-salient features. In addition, due to the lack of Co-SOD training data, we design a jigsaw training strategy, with which Co-SOD networks can be trained on general saliency datasets without extra pixel-level annotations. To evaluate the performance of Co-SOD methods on discovering the co-salient object among multiple foregrounds, we construct a challenging CoCA dataset, where each image contains at least one extraneous foreground along with the co-salient object. Experiments demonstrate that our GICD achieves state-of-the-art performance. Our codes and dataset are available at https://mmcheng.net/gicd/.<br />Comment: Accepted by ECCV 2020
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....9647d61e650360e3b94f9bad1a7e6eb5
- Full Text :
- https://doi.org/10.48550/arxiv.2004.13364