AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Debiased Textual Prompt Tuning for Enhancing Unknown Class Discovery

Yuxin Fan, Junbiao Cui, Changhao Liu, Xingwang Zhao, Jiye Liang

ECCV 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 0 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 textual prompt optimization (optimal-transport debiasing)TPOBGE · Hybridunknown samples misclassified as known: 2.9k -> 1.5kImproved
add textual prompt optimization (optimal-transport debiasing)TPOBGE · ImageNet-1Kunknown samples misclassified as known: 15k -> 1.6kImproved
add textual prompt optimization (ablation)TPOBGE · Hybrid, ImageNet-500, ImageNet-1K, Webvisionclustering accuracyImproved
add bimodal graph enhancement on top of prompt optimization (ablation)TPOBGE · Hybrid, ImageNet-500, ImageNet-1K, Webvisionclustering accuracyImproved
build bimodal proximity graph (more edges) (ablation)TPOBGE · Hybridedge count: 15.1k -> 114kImproved
build bimodal proximity graph (more edges) (ablation)TPOBGE · ImageNet-1Kedge count: 50k -> 375kImproved
vary tau_T, tau_I, k, beta one at a time (ablation)TPOBGE · Hybridclustering accuracyNo clear effect
replace CSC-OWSSL training with frozen encoders and prompt-only tuningTPOBGE · Hybridtraining time: 543 minutes -> 3 minutesImproved
replace CSC-OWSSL training with frozen encoders and prompt-only tuningTPOBGE · ImageNet-1Ktraining time: 7303 minutes -> 10 minutesImproved
TPOBGE versus SpectralGCD (best prior unknown-class average)TPOBGE · Average over 4 datasetsunknown-class accuracy: 54.03 -> 68.65Improved
TPOBGE versus SpectralGCD on HybridTPOBGE · Hybridall-class accuracy: 63.79 -> 63.81No 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