AI Paper Atlas

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

ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection

Erik Wallin, Lennart Svensson, Fredrik Kahl, Lars Hammarstrand

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 9 citations (OpenAlex)

Read the paper

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
use subspace score instead of energy score for ID/OOD detection (ablation)ProSub (end of warm-up) · CIFAR-100 / CIFAR-10AUROC: 0.65 -> 0.92Improved
use subspace score for a fully supervised model (ablation)fully supervised model · CIFAR-100 / CIFAR-10AUROC: 0.81 (energy) -> 0.73 (s)Hurt
replace angle score with residual distance or max similarity (ablation)ProSub · CIFAR-100 / CIFAR-10AUROC: 0.92 -> 0.88 (residual), 0.87 (max sim)Hurt
replace probabilistic ID/OOD with Otsu hard threshold (ablation)ProSub · CIFAR-100 (2,500 labels) / CIFAR-10AUROC: 0.97 -> 0.67Hurt
use predicted probabilities directly (weighted) instead of sampled ID mask (ablation)ProSub · CIFAR-100 (2,500 labels) / CIFAR-10accuracy: 74.11 -> 74.01No clear effect
add self-supervision loss l_self (ablation)ProSub · CIFAR-100 (10,000 labels) / CIFAR-10AUROC: 0.63 -> 0.87Improved
add subspace loss l_sub (ablation)ProSub · CIFAR-100 (10,000 labels) / CIFAR-10AUROC: 0.63 -> 0.96Improved
combine l_self and l_sub (ablation)ProSub · CIFAR-100 (10,000 labels) / CIFAR-10accuracy: 70.24 -> 79.46Improved
ProSub vs OpenMatch with CIFAR-10 as IDProSub · CIFAR-10 ID, 1,000 labelsAUROC: 0.92 vs 0.93Hurt

Later papers that compared with this method

3 later accepted papers report ProSub as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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