Research map / Vision-language and multimodal / CLIP and zero-shot
LICO: Explainable Models with Language-Image COnsistency
Yiming Lei, Zilong Li, Yangyang Li, Junping Zhang, Hongming Shan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LICO | ResNet-50 · ImageNet-1k top-1 | accuracy (%): 76.13 -> 76.27 | Improved |
| add GCC | ResNet-50 · ImageNet-1k top-1 | accuracy (%): 76.13 -> 74.40 | Hurt |
| add CGC | ResNet-50 · ImageNet-1k top-1 | accuracy (%): 76.13 -> 74.60 | Hurt |
| add LICO | ViT-Base-16 · ImageNet-1k accuracy | accuracy (%): 77.9 -> 78.2 | Improved |
| add LICO | Grad-CAM · ImageNet insertion | Insertion AUC: 53.5 -> 57.1 | Improved |
| add LICO | Group-CAM · ImageNet insertion | Insertion AUC: 56.8 -> 55.2 | Hurt |
| add LICO | Grad-CAM · ImageNet deletion | Deletion AUC: 13.3 -> 15.1 | Hurt |
| add LICO with 40 labels | WRN · CIFAR-10 | accuracy (%): 23.4 -> 24.9 | Improved |
| add LICO | PARN18 · CIFAR-100 2500 labels | accuracy (%): 23.7 -> 21.4 | Hurt |
| add LICO | WRN · CIFAR-100 full | accuracy (%): 80.9 -> 82.2 | Improved |
| use only L_OT without L_MM (ablation) | LICO · ImageNet top-1 | accuracy (%): 76.27 -> 75.98 | Hurt |
| use 12 context tokens instead of 0 (ablation) | LICO · ImageNet top-1 | accuracy (%): 75.64 -> 76.27 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Grad-CAM — Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization (ICCV 2017) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Explainable Saliency: Articulating Reasoning with Contextual Prioritization (CVPR 2025 · similarity 0.86)
- Reproducibility study of “LICO: Explainable Models with Language-Image Consistency" (NeurIPS 2024 · similarity 0.86)
- Explaining Domain Shifts in Language: Concept Erasing for Interpretable Image Classification (CVPR 2025 · similarity 0.85)
- Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models (CVPR 2025 · similarity 0.85)
- Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward (CVPR 2026 · similarity 0.85)
- CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
