Papers › Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model

1 Mar 2024arXiv:2403.00376archive 2025-07-28

Huan Ma, Yan Zhu, Changqing Zhang, Peilin Zhao, Baoyuan Wu, Long-Kai Huang, QinGhua Hu, Bingzhe Wu

Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of ``decision shortcuts'' that hinder their generalization capabilities. In this work, we find that the CLIP model possesses a rich set of features, encompassing both \textit{desired invariant causal features} and \textit{undesired decision shortcuts}. Moreover, the underperformance of CLIP on downstream tasks originates from its inability to effectively utilize pre-trained features in accordance with specific task requirements. To address this challenge, we propose a simple yet effective method, Spurious Feature Eraser (SEraser), to alleviate the decision shortcuts by erasing the spurious features. Specifically, we introduce a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit invariant features while disregarding decision shortcuts during the inference phase. The proposed method effectively alleviates excessive dependence on potentially misleading spurious information. We conduct comparative analysis of the proposed method against various approaches which validates the significant superiority.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mahuanaaa/intta officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fine-Grained Image ClassificationImage ClassificationLanguage ModellingTest-time Adaptationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections