VLG-CBM：采用视觉-语言引导训练概念瓶颈模型
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
AI总结：
针对现有概念瓶颈模型存在的概念预测不匹配、信息泄漏导致解释不可信的问题，提出视觉-语言引导的VLG-CBM框架，结合开放域接地目标检测器实现视觉接地概念标注，提出NEC指标控制信息泄漏，在五个基准上显著提升准确率并保障概念的可信性与可解释性。
摘要：
概念瓶颈模型（CBMs）通过引入中间概念瓶颈层（CBL）实现可解释预测，该层对人类可理解的概念进行编码以解释模型决策。近期研究提出利用大语言模型和预训练视觉-语言模型实现CBM的自动化训练，使其更具可扩展性和自动化程度。然而现有方法仍存在两方面不足：其一，CBL预测的概念往往与输入图像不匹配，引发对解释可信度的质疑；其二，研究表明概念值会编码非预期信息——即便一组随机概念也能达到与当前最优CBM相当的测试准确率。为解决这些关键局限，本文提出名为视觉-语言引导概念瓶颈模型（VLG-CBM）的新型框架，在提升性能的同时实现可信可解释性。该方法利用现成的开放域接地目标检测器提供视觉接地的概念标注，在大幅增强概念预测可信度的同时进一步提升模型性能。此外，本文提出名为有效概念数量（NEC）的新指标，用于控制信息泄漏并提供更优的可解释性。在五个标准基准上的广泛评估表明，本文提出的VLG-CBM方法在NEC=5时的准确率（记为ANEC-5）上比现有方法至少高出4.27%，最高提升51.09%；在平均准确率（记为ANEC-avg）上至少高出0.45%，最高提升29.78%，同时大量实验证明其保留了所学概念的可信度与可解释性。
英文摘要：
Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes human-understandable concepts to explain models' decision. Recent works proposed to utilize Large Language Models and pre-trained Vision-Language Models to automate the training of CBMs, making it more scalable and automated. However, existing approaches still fall short in two aspects: First, the concepts predicted by CBL often mismatch the input image, raising doubts about the faithfulness of interpretation. Second, it has been shown that concept values encode unintended information: even a set of random concepts could achieve comparable test accuracy to state-of-the-art CBMs. To address these critical limitations, in this work, we propose a novel framework called Vision-Language-Guided Concept Bottleneck Model (VLG-CBM) to enable faithful interpretability with the benefits of boosted performance. Our method leverages off-the-shelf open-domain grounded object detectors to provide visually grounded concept annotation, which largely enhances the faithfulness of concept prediction while further improving the model performance. In addition, we propose a new metric called Number of Effective Concepts (NEC) to control the information leakage and provide better interpretability. Extensive evaluations across five standard benchmarks show that our method, VLG-CBM, outperforms existing methods by at least 4.27% and up to 51.09% on Accuracy at NEC=5 (denoted as ANEC-5), and by at least 0.45% and up to 29.78% on average accuracy (denoted as ANEC-avg), while preserving both faithfulness and interpretability of the learned concepts as demonstrated in extensive experiments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
