重新思考显著性引导的弱监督语义分割
Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
AI总结：
本文通过实证分析揭示显著性图质量与阈值选择对 WSSS 的关键影响，并提出统一标准化框架 WSSS-BED，以支持更严谨的显著性引导弱监督语义分割研究。
摘要：
本文针对显著性图在弱监督语义分割（WSSS）中的作用提出了全新视角，并基于实证发现给出了新的见解和研究方向。我们开展了全面实验，观察到显著性图的质量是显著性引导 WSSS 方法中的关键因素。尽管如此，我们发现以往工作中使用的显著性图往往是任意选择的，无视其对 WSSS 的显著影响。此外，我们观察到此前较少受到关注的阈值选择在 WSSS 中并非无关紧要。为了促进显著性引导 WSSS 更有意义且更严谨的研究，我们引入了 WSSS-BED，这是一个在统一条件下开展研究的标准化框架。WSSS-BED 为七种 WSSS 方法提供多种显著性图和激活图，并提供来自无监督显著目标检测模型的显著性图。
英文摘要：
This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our empirical findings. We conduct comprehensive experiments and observe that the quality of the saliency map is a critical factor in saliency-guided WSSS approaches. Nonetheless, we find that the saliency maps used in previous works are often arbitrarily chosen, despite their significant impact on WSSS. Additionally, we observe that the choice of the threshold, which has received less attention before, is non-trivial in WSSS. To facilitate more meaningful and rigorous research for saliency-guided WSSS, we introduce \texttt{WSSS-BED}, a standardized framework for conducting research under unified conditions. \texttt{WSSS-BED} provides various saliency maps and activation maps for seven WSSS methods, as well as saliency maps from unsupervised salient object detection models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
