计算机科学与探索2025，Vol.19Issue(11)：2950-2966,17.DOI:10.3778/j.issn.1673-9418.2503023
变分信息瓶颈引导的互补概念瓶颈模型
Variational Information Bottleneck-Guided Complementary Concept Bottleneck Model
摘要
Abstract
Concept bottleneck models(CBMs)project visual features extracted from black-box models onto a set of human-interpretable concepts to facilitate decision-making.Existing approaches typically rely on large language models(LLMs)to generate textual concepts and on multimodal pretrained models to align visual features with text embeddings.However,these methods often introduce textual noise into the bottleneck,resulting in explanations that may not accurately reflect the image content or its visual attributes.To address this limitation,a variational information bottleneck-guided complementary concept bottleneck model is proposed.This method employs a chain-of-thought(CoT)-based concept generation strategy that prompts both vision-language models(VLMs)and LLMs to produce more precise and complementary textual descriptions.A concept selection module based on variational information bottleneck feature attribution method is then developed to extract the textual concepts most relevant to the image content.Furthermore,an image classification strategy is designed that integrates dual-branch concept activation scores from complementary concept bottlenecks to support robust decision-making.Finally,an interpretability efficiency metric is introduced to evaluate the succinctness and effectiveness of the generated explanations.Experimental results on six public datasets demonstrate that the proposed method not only outperforms five state-of-the-art models in interpretability efficiency,but also achieves comparable or even superior classification accuracy.关键词
概念瓶颈模型/变分信息瓶颈/特征归因/可解释性Key words
concept bottleneck models/variational information bottleneck/feature attribution/interpretability分类
计算机与自动化引用本文复制引用
冀中,林子杰..变分信息瓶颈引导的互补概念瓶颈模型[J].计算机科学与探索,2025,19(11):2950-2966,17.基金项目
国家自然科学基金(62176178). This work was supported by the National Natural Science Foundation of China(62176178). （62176178）
