“LICO：具有语言-图像一致性的可解释模型”的可复现性研究
Reproducibility study of "LICO: Explainable Models with Language-Image Consistency"
- University of Amsterdam（阿姆斯特丹大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文复现了LICO方法，发现其未能一致提升图像分类性能与可解释性指标，强调了可解释性研究中严格评估和透明报告的重要性。
AI中文摘要：
机器学习中日益严重的可复现性危机促使人们需要仔细审视研究发现。本文考察了Lei等人（2023）关于其提出的LICO方法的论断，该方法旨在增强事后可解释性技术并提升图像分类性能。LICO利用来自视觉-语言模型的自然语言监督来丰富特征表示并引导学习过程。我们开展了一项全面的可复现性研究，采用了（宽）ResNet以及Grad-CAM和RISE等既有可解释性方法。我们大多未能复现作者的结果。特别是，我们没有发现LICO能够一致地带来分类性能的提升，或在可解释性的定量和定性指标上带来改善。因此，我们的发现凸显了在可解释性研究中进行严格评估和透明报告的重要性。
英文摘要：
The growing reproducibility crisis in machine learning has brought forward a need for careful examination of research findings. This paper investigates the claims made by Lei et al. (2023) regarding their proposed method, LICO, for enhancing post-hoc interpretability techniques and improving image classification performance. LICO leverages natural language supervision from a vision-language model to enrich feature representations and guide the learning process. We conduct a comprehensive reproducibility study, employing (Wide) ResNets and established interpretability methods like Grad-CAM and RISE. We were mostly unable to reproduce the authors' results. In particular, we did not find that LICO consistently led to improved classification performance or improvements in quantitative and qualitative measures of interpretability. Thus, our findings highlight the importance of rigorous evaluation and transparent reporting in interpretability research.
