AI Paper Atlas

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

Beyond Retraining: Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision–Language Models

Yongguang Li, Jindong Li, Qi Wang, QianLi Xing, Runliang Niu, Shengsheng Wang, Menglin Yang

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 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
add SUFF unknown-subspace filtering to CLIP (ablation)CLIP zero-shot with threshold · Office-Home + VisDA, avg over thresholdsHOS (%): 72.4 -> 80.1Improved
add SUFF to SigLIP (ablation)SigLIP zero-shot · Office-Home + VisDA, avg over thresholdsHOS (%): 67.1 -> 73.9Improved
add SUFF to ALIGN (ablation)ALIGN zero-shot · Office-Home + VisDA, avg over thresholdsHOS (%): 72.8 -> 77.7Improved
add SUFF (ablation)CLIP · VTAB-6, Office-Home, VisDAAR@1: 0.46 -> 0.23Improved
use BGAT instead of fixed threshold (CLIP, no SUFF) (ablation)CLIP · Office-Home + VisDA avgHOS (%): 66.9 -> 76.4Improved
use BGAT instead of fixed threshold (SigLIP, no SUFF) (ablation)SigLIP · Office-Home + VisDA avgHOS (%): 52.1 -> 80.0Improved
use BGAT instead of k-means threshold (CLIP, no SUFF) (ablation)CLIP · Office-Home + VisDA avgHOS (%): 74.0 -> 76.4Improved
add Box-Cox transformation before GMM thresholding (ablation)BGAT · Office-Home + VisDA, 3 VLMsHOS (%): avg gain 2.67%Improved
add BGAT to UEO-CLIPUEO-CLIP · Office-Home (4 domains avg)HOS (%): 67.0 -> 75.9Improved
add SUFF on top of BGAT to UEO-CLIPUEO-CLIP · Office-Home (4 domains avg)HOS (%): 75.9 -> 78.8Improved
add BGAT and SUFF to SHOTSHOT · Office-Home (4 domains avg)HOS (%): 57.8 -> 62.9Improved
vary variance retention ratio tau in 0.7-0.9 (ablation)SUFF · Office-Home + VisDA avgHOS (%): variance 0.19 (%)^2No 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