paper-with-me

Papers

Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts

2025-03-08 · Yubin Wang, Xinyang Jiang, De Cheng, Xiangqian Zhao, Zilong Wang, Dongsheng Li, Cairong Zhao

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.

📄 PDF Abstract BibTeX arXiv:2503.06084

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Prompt Tuning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning

2024-12-22 · Haowei Zhu, Fangyuan Zhang, Rui Qin, Tianxiang Pan 외

As the scale of vision models continues to grow, Visual Prompt Tuning (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance compared to full fine-tuning. However, indi…

Attributeparameter-efficient fine-tuningTransfer LearningVisual Prompt Tuning

XPrompt: Exploring the Extreme of Prompt Tuning

2022-10-10 · Fang Ma, Chen Zhang, Lei Ren, Jingang Wang 외

Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of…

TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding

2023-05-19 · Chenchi Zhang, Jun Xiao, Lei Chen, Jian Shao 외

Prompt tuning has achieved great success in transferring the knowledge from large pretrained vision-language models into downstream tasks, and has dominated the performance on visual grounding (VG). However, almost all e…

SentenceVisual Grounding

Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition

2024-02-23 · Haodong Zhao, Ruifang He, Mengnan Xiao, Jing Xu

Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical discourse relations among arguments. Previous methods achieve the promotion through fine-tuning PLMs. However, due to the data …

ProTeCt: Prompt Tuning for Taxonomic Open Set Classification

2023-06-04 · CVPR 2024 1 · Tz-Ying Wu, Chih-Hui Ho, Nuno Vasconcelos

Visual-language foundation models, like CLIP, learn generalized representations that enable zero-shot open-set classification. Few-shot adaptation methods, based on prompt tuning, have been shown to further improve perfo…

Classificationopen-set classification