Pixel Is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection
Zhenyu Wu, Lin Wang, Wei Wang, 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 trajectory-ensemble active learning (ATAL). Our contributions are three-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 trajectory-ensemble uncertainty estimation method maintains the advantages of the ensemble networks while significantly reducing the computational cost. 3) Our proposed relationship-aware diversity sampling algorithm can conquer oversampling while boosting performance. Experimental results show that our ATAL can find such a point-labeled dataset, where a saliency model trained on it obtained 97%-99% performance of its fully-supervised version with only 10 annotated points per image.
BibTeX
@article{Wu_Wang_Wang_Xia_Chen_Hao_Li_2023, title={Pixel Is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25390}, DOI={10.1609/aaai.v37i3.25390}, abstractNote={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 trajectory-ensemble active learning (ATAL). Our contributions are three-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 trajectory-ensemble uncertainty estimation method maintains the advantages of the ensemble networks while significantly reducing the computational cost. 3) Our proposed relationship-aware diversity sampling algorithm can conquer oversampling while boosting performance. Experimental results show that our ATAL can find such a point-labeled dataset, where a saliency model trained on it obtained 97%-99% performance of its fully-supervised version with only 10 annotated points per image.}, number={3}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wu, Zhenyu and Wang, Lin and Wang, Wei and Xia, Qing and Chen, Chenglizhao and Hao, Aimin and Li, Shuo}, year={2023}, month={Jun.}, pages={2883-2891} }