AI Paper Atlas

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

LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning

Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa

NeurIPS 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 12 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 local-feature OOD regularization (LoCoOp) to CoOp, GL-MCM score, 16-shotCoOp · ImageNet-1K OOD benchmarksFPR95: 30.67 -> 28.66Improved
add local-feature OOD regularization, MCM score, 16-shotCoOp · ImageNet-1K OOD benchmarksFPR95: 36.83 -> 33.98Improved
add local-feature OOD regularization, 1-shot, GL-MCMCoOp · ImageNet-1K OOD benchmarksFPR95: 36.58 -> 33.52Improved
add OOD regularization on ResNet-50 backbone, 16-shotCoOp_GL · ImageNet-1K OOD benchmarksFPR95: 38.27 -> 34.45Improved
add OOD regularization on ImageNet-100 ID, 16-shotCoOp_GL · ImageNet-100 OODFPR95: 13.82 -> 10.77Improved
use LoCoOp instead of CoCoOpprompt learning OOD detection · ImageNet-1K OOD, 16-shotFPR95 and inference time: 35.53 -> 33.98 FPR95; 149 ms -> 2.59 msImproved
add OOD regularizationCoOp · ImageNet-1K val, 16-shottop-1 ID accuracy: 72.1 -> 71.7Hurt
use rank-based top-K extraction of ID-irrelevant regions instead of entropy-based thresholding (ablation)LoCoOp_GL · ImageNet-1K OOD, 16-shotFPR95: 36.38 -> 28.66Improved
use rank-based instead of probability-based region extraction (ablation)LoCoOp_GL · ImageNet-1K OOD, 16-shotFPR95: 28.65 -> 28.66No clear effect
treat all local regions as OOD (K=0) instead of K=200 (ablation)LoCoOp · ImageNet-1K OOD, 16-shotdetection performanceHurt
vary K between 200 and 980 (ablation)LoCoOp · ImageNet-1K OOD, 16-shotdetection performanceNo clear effect
set lambda below 1 (0.25) instead of 1 (ablation)LoCoOp · ImageNet-1K OOD, 16-shotFPR95 / AUROCImproved

Later papers that compared with this method

11 later accepted papers report LoCoOp as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.

3 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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