Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts
This addresses the problem of AI reliability and knowledge discovery for users of visual foundation models, though it is incremental as it builds on existing prompt tuning methods.
The paper tackled the lack of interpretability in visual prompt tuning by proposing Interpretable Visual Prompt Tuning (IVPT), which links prompts to hierarchical concept prototypes, resulting in superior interpretability and performance on fine-grained classification benchmarks.
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for enhancing AI reliability and enabling AI-driven knowledge discovery. In this paper, rather than learning abstract prompt embeddings, we propose the first framework, named Interpretable Visual Prompt Tuning (IVPT), to explore interpretability for visual prompts, by introducing hierarchical concept prototypes. Specifically, visual prompts are linked to human-understandable semantic concepts, represented as a set of category-agnostic prototypes, each corresponding to a specific region of the image. Then, IVPT aggregates features from these regions to generate interpretable prompts, which are structured hierarchically to explain visual prompts at different granularities. Comprehensive qualitative and quantitative evaluations on fine-grained classification benchmarks show its superior interpretability and performance over conventional visual prompt tuning methods and existing interpretable methods.