Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
IEEE Transactions on Knowledge and Data Engineering(2023)
摘要
Previous weakly-supervised object localization (WSOL) methods aim to expand
activation map discriminative areas to cover the whole objects, yet neglect two
inherent challenges when relying solely on image-level labels. First, the
“entangled context” issue arises from object-context co-occurrence (, fish
and water), making the model inspection hard to distinguish object boundaries
clearly. Second, the “C-L dilemma” issue results from the information decay
caused by the pooling layers, which struggle to retain both the semantic
information for precise classification and those essential details for accurate
localization, leading to a trade-off in performance. In this paper, we propose
a knowledge-guided causal intervention method, dubbed KG-CI-CAM, to address
these two under-explored issues in one go. More specifically, we tackle the
co-occurrence context confounder problem via causal intervention, which
explores the causalities among image features, contexts, and categories to
eliminate the biased object-context entanglement in the class activation maps.
Based on the disentangled object feature, we introduce a multi-source knowledge
guidance framework to strike a balance between absorbing classification
knowledge and localization knowledge during model training. Extensive
experiments conducted on several benchmark datasets demonstrate the
effectiveness of KG-CI-CAM in learning distinct object boundaries amidst
confounding contexts and mitigating the dilemma between classification and
localization performance.
更多查看译文
关键词
Object Localization,Weakly-supervised Learning,Knowledge Guidance,Causal Intervention
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要