AI Paper Atlas

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

Can OOD Object Detectors Learn from Foundation Models?

Jiahui Liu, Xin Wen, Shizhen Zhao, Yingxian Chen, Xiaojuan Qi

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 14 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 similarity-based filter for selecting synthetic OOD objects (ablation)SyncOOD · PASCAL-VOC (ID) vs MS-COCOFPR95: 39.29 -> 36.44Improved
add SAM-based box refiner (ablation)SyncOOD · PASCAL-VOC (ID) vs MS-COCOFPR95: 39.55 -> 36.44Improved
inpaint ID objects in scene images instead of generating object-centric images (ablation)SyncOOD · PASCAL-VOC (ID) vs MS-COCOFPR95: 51.99 -> 36.44Improved
use object boxes rather than whole edited scene image as OOD sample (ablation)SyncOOD · PASCAL-VOC (ID) vs MS-COCOFPR95: 48.01 -> 36.44Improved
increase number of synthetic samples from 4k to 14k (ablation)SyncOOD · PASCAL-VOC (ID) vs MS-COCOFPR95: 36.44 -> 36.70No clear effect
vary number of imagined novel concepts per ID object (3 to 8) (ablation)SyncOOD · PASCAL-VOC (ID) vs MS-COCOFPR95: 36.96 to 37.91No clear effect
train SyncOOD OOD detector on top of Faster R-CNN instead of SAFEFaster R-CNN OOD detection · PASCAL-VOC (ID) vs MS-COCOFPR95: 50.86 -> 36.44Improved
SyncOOD vs DFDD on AUROC for PASCAL-VOC / MS-COCOSyncOOD · PASCAL-VOC (ID) vs MS-COCOAUROC: 90.79 vs 86.52Hurt

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