Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models
This work addresses the generalization issue in few-shot image classification for vision-language models, representing an incremental improvement over existing prompt tuning methods.
The paper tackles the problem of vision-language models overfitting to seen classes and failing to generalize to unseen ones by proposing a Knowledge-Aware Prompt Tuning (KAPT) framework, which achieves an absolute gain of 3.22% on new classes and 2.57% in harmonic mean compared to the state-of-the-art CoCoOp method.
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.