AI Paper Atlas

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

Adaptive Prompt Learning via Gaussian Outlier Synthesis for Out-of-distribution Detection

Yongkang Zhang, Dongyu She, Zhong Zhou

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 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 location tokens to the CLIP-style prompt (ablation)APLGOS prompts · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 51.31 / 50.96 -> 49.56 / 47.60Improved
initialize prompts from ChatGPT-sampled statements instead of "a region of a" (ablation)APLGOS prompts · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 51.31 / 50.96 -> 49.50 / 49.40Improved
combine location tokens and sampled statements (full prompt) (ablation)APLGOS prompts · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 49.56 / 47.60 -> 45.96 / 47.10Improved
use only class label as prompt vs full APLGOS prompt (ablation)APLGOS prompts · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)mAP (ID): 48.2 -> 49.4Improved
APLGOS over VOS baseline (RegNetX4.0) (ablation)VOS · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 50.53 / 50.27 -> 45.96 / 47.10Improved
APLGOS over VOS baseline (ResNet50) (ablation)VOS · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 48.28 / 52.14 -> 47.16 / 49.66Improved
APLGOS over VOS (RegNetX4.0) on BDD100k (ablation)VOS · Berkeley DeepDrive-100k (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 42.82 / 27.55 -> 39.48 / 19.79Improved
add Gaussian noise strength alpha=1.0 vs none (ablation)APLGOS OOD prompt sampling · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 51.63 / 50.88 -> 45.96 / 47.10Improved
increase noise strength alpha from 1.0 to 1.5 (ablation)APLGOS OOD prompt sampling · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 45.96 / 47.10 -> 55.88 / 53.33Hurt
increase ID:OOD ratio from 1:1 to 3:1 (ablation)APLGOS training data · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)mAP (ID): 49.4 -> 47.5Hurt
increase ID:OOD ratio from 1:1 to 2:1 (baseline ratio) (ablation)APLGOS training data · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95: 45.96 / 47.10 -> 48.25 / 50.20Hurt
vary number of sampled OOD prompts K around default 10000 (ablation)APLGOS OOD prompt sampling · PASCAL VOC (ID) vs MS-COCO2017 / OpenImages (OOD)FPR95Mixed

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