Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption

TL;DR

This paper introduces UnInfo, a test-time adaptation method for vision-language models like CLIP, which enhances robustness against sensor degradation by maintaining embedding uniformity and information balance during adaptation.

Contribution

The paper proposes a novel uniformity-aware test-time adaptation method called UnInfo that specifically addresses sensor degradation in vision-language models, a challenge not tackled by existing methods.

Findings

UnInfo improves accuracy on sensor-degraded images.

Maintains embedding uniformity and information balance during adaptation.

Outperforms existing TTA methods under sensor degradation conditions.

Abstract

Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applications represented by zero-shot classification. However, vision-language models still suffer when they face datasets with large gaps from training ones, i.e., distribution shifts. We found that CLIP is especially vulnerable to sensor degradation, a type of realistic distribution shift caused by sensor conditions such as weather, light, or noise. Collecting a new dataset from a test distribution for fine-tuning highly costs since sensor degradation occurs unexpectedly and has a range of variety. Thus, we investigate test-time adaptation (TTA) of zero-shot classification, which enables on-the-fly adaptation to the test distribution with unlabeled test data. Existing TTA methods for CLIP mainly focus on modifying image and text embeddings or predictions to address distribution shifts. Although these methods can adapt to domain shifts, such as fine-grained labels spaces or different renditions in input images, they fail to adapt to distribution shifts caused by sensor degradation. We found that this is because image embeddings are "corrupted" in terms of uniformity, a measure related to the amount of information. To make models robust to sensor degradation, we propose a novel method called uniformity-aware information-balanced TTA (UnInfo). To address the corruption of image embeddings, we introduce uniformity-aware confidence maximization, information-aware loss balancing, and knowledge distillation from the exponential moving average (EMA) teacher. Through experiments, we demonstrate that our UnInfo improves accuracy under sensor degradation by retaining information in terms of uniformity.