English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Contemporary weakly-supervised object localization (WSOL) methods haveprimarily focused on addressing the challenge of localizing the mostdiscriminative region while largely overlooking the relatively less exploredissue of biased activation -- incorrectly spotlighting co-occurring backgroundwith the foreground feature. In this paper, we conduct a thorough causalanalysis to investigate the origins of biased activation. Based on ouranalysis, we attribute this phenomenon to the presence of co-occurringbackground confounders. Building upon this profound insight, we introduce apioneering paradigm known as Counterfactual Co-occurring Learning (CCL),meticulously engendering counterfactual representations by adeptlydisentangling the foreground from the co-occurring background elements.Furthermore, we propose an innovative network architecture known asCounterfactual-CAM. This architecture seamlessly incorporates a perturbationmechanism for counterfactual representations into the vanilla CAM-based model.By training the WSOL model with these perturbed representations, we guide themodel to prioritize the consistent foreground content while concurrentlyreducing the influence of distracting co-occurring backgrounds. To the best ofour knowledge, this study represents the initial exploration of this researchdirection. Our extensive experiments conducted across multiple benchmarksvalidate the effectiveness of the proposed Counterfactual-CAM in mitigatingbiased activation.

Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization