Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models

TL;DR

This paper introduces Test-Time Prototype Shifting (TPS), a novel method that dynamically adapts vision-language models to new test environments using unlabeled data, improving zero-shot classification accuracy efficiently.

Contribution

The paper proposes TPS, a test-time adaptation framework that modulates class prototypes for better zero-shot generalization without additional training or large resource use.

Findings

Achieves state-of-the-art results on 15 datasets with domain shifts.

Reduces memory and computational costs compared to prompt tuning.

Effectively bridges domain gaps in zero-shot classification.

Abstract

Advancements in vision-language models (VLMs) have propelled the field of computer vision, particularly in the zero-shot learning setting. Despite their promise, the effectiveness of these models often diminishes due to domain shifts in test environments. To address this, we introduce the Test-Time Prototype Shifting (TPS) framework, a pioneering approach designed to adapt VLMs to test datasets using unlabeled test inputs. Our method is based on the notion of modulating per-class prototypes in the shared embedding space. By pre-computing and caching prototypes generated with the pre-trained text encoder, TPS not only facilitates optimization-free prototype reuse for subsequent predictions but also enables seamless integration with current advancements in prompt engineering. At test-time, TPS dynamically learns shift vectors for each prototype based solely on the given test sample, effectively bridging the domain gap and enhancing classification accuracy. A notable aspect of our framework is its significantly reduced memory and computational demands when compared to conventional text-prompt tuning methods. Extensive evaluations across 15 image classification datasets involving natural distribution shifts and cross-dataset generalization, as well as in context-dependent visual reasoning, demonstrate TPS's superior performance, achieving state-of-the-art results while reducing resource requirements.