Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection

Zhenyu Wu, Wei Wang, Lin Wang, Yacong Li, Fengmao Lv, Qing Xia, Chenglizhao Chen, Aimin Hao, Shuo Li

Abstract

Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial spatio-temporal ensemble active learning. Our contributions are four-fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. 2) Our proposed spatio-temporal ensemble strategy not only achieves outstanding performance but significantly reduces the model's computational cost. 3) Our proposed relationship-aware diversity sampling can conquer oversampling while boosting model performance. 4) We provide theoretical proof for the existence of such a point-labeled dataset. Experimental results show that our approach can find such a point-labeled dataset, where a saliency model trained on it obtained 98%–99% performance of its fully-supervised version with only ten annotated points per image.
BibTeX
@article{wu2025pixel,
  author = {Zhenyu Wu and Wei Wang and Lin Wang and Yacong Li and Fengmao Lv and Qing Xia and Chenglizhao Chen and Aimin Hao and Shuo Li},
  title = {{Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2025},
  doi = {10.1109/tpami.2024.3476683},
}

Loading related content...

Figure