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

TL;DR

This paper introduces Spurious Feature Eraser, a test-time prompt tuning method that enhances vision-language models' robustness by removing spurious features, thereby improving their generalization on downstream tasks.

Contribution

The paper proposes a novel test-time prompt tuning approach to erase spurious features, improving the generalization of vision-language models like CLIP on downstream tasks.

Findings

Significant performance improvements over existing methods.

Effective suppression of decision shortcuts during inference.

Enhanced reliance on invariant causal features.

Abstract

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.