Pixel-Level Noise Mining for Weakly Supervised Salient Object Detection

Training a deep model for visual saliency detection requires the collection and labor-intensive annotation of overwhelmingly large data. We propose to learn saliency detection in a weakly supervised manner from single noisy label, which is easy to obtain from unsupervised handcrafted feature-based methods. However, deep networks tend to overfit such noises leading to a dramatic drop in accuracy. Given our goal, we address a natural question: can we identify outliers during network prediction and rectify the label noises? To this end, we propose a pixel-level noise mining framework for robust salient object detection (SOD) by exploiting its own knowledge, and without the need for external models. Specifically,…

• NN
  National Natural Science Foundation of China

  Awards: 62403189, 62373293, 62463020
• NS
  Natural Science Foundation of Jiangxi Province

  Award: 20242BAB20050
• WS
  Wuhan Science and Technology Project

  Awards: 20233TGV06020, 20232ACC01007