Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models

TL;DR

This paper introduces a Knowledge-Aware Prompt Tuning framework for vision-language models that incorporates external knowledge to improve generalization to unseen classes, especially in few-shot image classification tasks.

Contribution

The paper proposes a novel knowledge-aware prompt tuning method that leverages external knowledge and visual cues to enhance model generalization to unseen categories.

Findings

Significant improvement in unseen class generalization

Achieves 3.22% absolute gain over state-of-the-art on new classes

Effective across 11 benchmark datasets

Abstract

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes, failing to generalize to unseen classes. In this paper, we propose a Knowledge-Aware Prompt Tuning (KAPT) framework for vision-language models. Our approach takes inspiration from human intelligence in which external knowledge is usually incorporated into recognizing novel categories of objects. Specifically, we design two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge. The discrete prompt extracts the key information from descriptions of an object category, and the learned continuous prompt captures overall contexts. We further design an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations. We conduct extensive experiments on 11 widely-used benchmark datasets and the results verify the effectiveness in few-shot image classification, especially in generalizing to unseen categories. Compared with the state-of-the-art CoCoOp method, KAPT exhibits favorable performance and achieves an absolute gain of 3.22% on new classes and 2.57% in terms of harmonic mean.