Weakly-Supervised Salient Object Detection via Scribble Annotations

By Jing Zhang, Xin Yu, Aixuan Li, Peipei Song, Bowen Liu, Yuchao Dai. Computer Vision and Pattern Recognition, 2020

314 citations recorded by the source corpus.

Compared with laborious pixel-wise dense labeling, it is much easier to label data by scribbles, which only costs 1~2 seconds to label one image. However, using scribble labels to learn salient object detection has not been explored. In this paper, we propose a weakly-supervised salient object detection model to learn saliency from such annotations. In doing so, we first relabel an existing large-scale salient object detection dataset with scribbles, namely S-DUTS dataset. Since object structure and detail information is not identified by scribbles, directly training with scribble labels will lead to saliency maps of poor boundary localization. To mitigate this problem, we propose an auxiliary edge detection task to localize object edges explicitly, and a gated structure-aware loss to place constraints on the scope of structure to be recovered. Moreover, we design a scribble boosting scheme to iteratively consolidate our scribble annotations, which are then employed as supervision to learn high-quality saliency maps. As existing saliency evaluation metrics neglect to measure structure alignment of the predictions, the saliency map ranking may not comply with human perception. We present a new metric, termed saliency structure measure, as a complementary metric to evaluate sharpness of the prediction. Extensive experiments on six benchmark datasets demonstrate that our method not only outperforms existing weakly-supervised/unsupervised methods, but also is on par with several fully-supervised state-of-the-art models (Our code and data is publicly available at: https://github.com/JingZhang617/Scribble_Saliency).

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b22e74be741d7852c995348e566bef58b9a3d40b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

  1. Deng-Ping Fan
  2. Yuchao Dai
  3. Nick Barnes
  4. Jing Zhang
  5. Saeed Anwar
  6. Ling Shao
  7. Ming-Ming Cheng

In Computer Vision and Pattern Recognition

  1. Deng-Ping Fan
  2. Yuchao Dai
  3. Nick Barnes
  4. Jing Zhang
  5. Saeed Anwar
  6. Tong Zhang
  7. F. Saleh
  8. Ling Shao

Citations in the corpus