AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

Yushu Li, Xun Xu, Yongyi Su, Kui Jia

ICCV 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Realistic and stable test-time adaptation · 27 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 distribution alignment on top of prototype clustering and expansion (ablation)OWTTT · CIFAR10-C + noiseAcc_H: 81.4 -> 91.6Improved
add prototype expansion to prototype clustering (ablation)OWTTT · CIFAR10-C + SVHNAcc_H: 72.7 -> 77.4Improved
add plain prototype clustering with source prototypes only (ablation)OWTTT with O.D. · CIFAR10-C + noiseAcc_H: 81.4 -> 76.1Hurt
enable strong OOD detector at inference (ablation)TEST baseline · CIFAR10-C + noiseAcc_N: 0.0 -> 100.0Improved
use adaptive threshold tau* instead of fixed thresholds 0.1 to 0.9 (ablation)strong OOD pruning · CIFAR10-C with strong OODstrong OOD detectionImproved
use distribution alignment (BN, TTAC) instead of self-training (TENT, SHOT)baselines under strong OOD · CIFAR10-CAcc_H: BN 85.11 vs TENT 32.77 (noise)Improved
vary ratio of strong to weak OOD from 0.2 to 1.0 (ablation)OWTTT · CIFAR10-CAcc_H: noise 90.83 -> 91.34No clear effect
enable OOD detector when target has no strong OOD (ablation)OWTTT · clean CIFAR10-CAcc_S: 85.25 -> 78.63Hurt
OWTTT vs best baselines on ImageNet-C noiseOWTTT · ImageNet-C + noiseAcc_H: SHOT 63.75 vs Ours 58.56Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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