AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Verbalized Representation Learning for Interpretable Few-Shot Generalization

Cheng-Fu Yang, Da Yin, Wenbo Hu, Heng Ji, Nanyun Peng, Bolei Zhou, Kai-Wei Chang

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add commonality features F_comm to difference features F_diff (ablation)VRL · iNaturalist feature fusion (avg)accuracy: 65.26 -> 67.92Improved
add CLIP image features to F_diff and F_comm (ablation)VRL (concat) · iNaturalist feature fusion (avg)accuracy: 67.92 -> 73.92Improved
ensemble per-feature classifiers instead of concatenation (ablation)VRL · iNaturalist feature fusion (avg)accuracy: 73.92 -> 76.52Improved
soft voting instead of hard voting (LR, LR, MLP) (ablation)VRL ensemble · iNaturalist feature fusion (avg)accuracy: 71.60 -> 76.52Improved
add DINO features to F_diff, F_comm and CLIP (ablation)VRL ensemble · iNaturalist feature fusion (avg)accuracy: 76.52 -> 79.92Improved
use VRL instead of LLaVA SFTLLaVA · iNaturalist (10 images per class)accuracy: 43.9 -> 62.1Improved
use VRL instead of LLaVA SFTLLaVA · iNaturalist (200 images per class)accuracy: 80.2 -> 86.2Improved
use VRL instead of in-context learningLLaVA-7B · iNaturalist (5 families)accuracy: 22.92 -> 58.46Improved
use VRL-extracted features instead of human-labeled attributesVRL · Kiki-Bouba (human attributes comparison)accuracy: 63.15 -> 83.00Improved
scale VRL from 7B to 72B (ablation)LLaVA-VRL · iNaturalist (5 families)accuracy: 58.46 -> 67.92Improved
scale VRL from 7B to 72B (ablation)LLaVA-VRL · Kiki-Bouba (avg of 2 splits)accuracy: 83.00 -> 81.90No clear effect
use LLaVA instead of CLIP (binary) for feature mapping with LR (ablation)VRL · iNaturalistaccuracy: 58.0 -> 67.4Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy