AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection

Amirhossein Ansari, Ke Wang, Pulei Xiong

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 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 negative label filtering (NegFilter) (ablation)CSP · ImageNet-1K ID, average over 4 OOD setsFPR95: 34.47 -> 31.88Improved
add multi-matching score S_MM (ablation)CSP · ImageNet-1K ID, average over 4 OOD setsFPR95: 34.47 -> 31.70Improved
add both NegFilter and S_MM (ablation)CSP · ImageNet-1K ID, average over 4 OOD setsFPR95: 34.47 -> 30.12Improved
add proper nouns check C1 to NegFilter (ablation)NegRefine (S_MM on) · ImageNet-1K ID, average over 4 OOD setsFPR95: 31.70 -> 31.09Improved
add subcategory check C2 to NegFilter (ablation)NegRefine (S_MM on) · ImageNet-1K ID, average over 4 OOD setsFPR95: 31.70 -> 30.82Improved
combine both filter checks C1 and C2 (ablation)NegRefine (S_MM on) · ImageNet-1K ID, average over 4 OOD setsFPR95: 31.70 -> 30.12Improved
swap the LLM used for filtering (Qwen2.5-14B vs Mistral, Llama-3-8B, Qwen2.5-7B) (ablation)NegFilter · ImageNet-1K ID, average over 4 OOD setsAUROC: 91.79 vs 91.74-91.99No clear effect
increase k from 1 to 2 in multi-matching texts (ablation)S_MM · ImageNet-1K ID, average over 4 OOD setsFPR95: 36.86 -> 31.94Improved
use S_MM instead of local-feature score S_L (ablation)NegLabel score · ImageNet-1K ID, average over 4 OOD setsAUROCImproved
replace sigmoid-style exp ratio max with sum over matching texts (ablation)S_MM · ImageNet-1K ID, average over 4 OOD setsFPR95: 30.12 -> 49.00Hurt
increase initial negative label percentage p from 15 to 100 (ablation)NegRefine · ImageNet-1K ID, average over 4 OOD setsFPR95: 30.12 -> 32.16Hurt
use NegRefine instead of CSP with ImageNet-10 as IDCSP · ImageNet-10 ID vs ImageNet-20 OODFPR95: 3.30 -> 3.89Hurt

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