Reproducibility study of “LICO: Explainable Models with Language-Image Consistency"
Abstract: 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.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: This is a short summary of the changes:
- Rewrote Introduction with reviewer's remarks
- Ran on Imagenet 20% subset
- Rewrote Methods section with own interpretation
- Added to the Discussion section with reviewers' remarks
- Added original images for saliency maps from the LICO paper
- Added original Figure 1
Assigned Action Editor: ~Pascal_Poupart2
Submission Number: 2248
Loading