AI Paper Atlas

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

SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias

Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, Aidong Zhang

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 1 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
select a prompt per image by separation score (top-1) instead of fixed default promptzero-shot CLIP models · Waterbirds (5-backbone avg)worst-group accuracy: 36.7 -> 44.9Improved
select a prompt per image by separation score on CelebAzero-shot CLIP models · CelebA (5-backbone avg)worst-group accuracy: 75.3 -> 80.6Improved
SAGE on PACS and VLCSzero-shot CLIP models · PACS / VLCS (5-backbone avg)worst-group accuracy: 75.5 -> 81.9 (PACS); 23.0 -> 33.8 (VLCS)Improved
SAGE average accuracy on VLCS vs zero-shotzero-shot CLIP models · VLCS (5-backbone avg)average accuracy: 76.1 -> 75.8No clear effect
use separation-score selection instead of random prompt selection (ablation)SAGE · Waterbirds (avg)worst-group accuracy: 40.1 -> 44.9Improved
use separation-score selection instead of random prompt selection (ablation)SAGE · CelebA (avg)worst-group accuracy: 74.9 -> 80.6Improved
use top-1 selected prompt instead of ensembling all 80 prompts (ablation)SAGE · Waterbirds (avg)worst-group accuracy: 36.2 -> 44.9Improved
use top-1 selected prompt instead of ensembling all 80 prompts (ablation)SAGE · CelebA (avg)worst-group accuracy: 73.2 -> 80.6Improved
increase number of selected prompts K above 1 (ablation)SAGE · Waterbirds, CelebAworst-group accuracyMixed
SAGE on CLIP-RN-50 WaterbirdsCLIP-RN-50 · Waterbirdsworst-group accuracy: 41.0 -> 41.3No clear effect

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