AI Paper Atlas

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

Neural Collapse in Test-Time Adaptation

Xiao Chen, Zhongjing Du, Jiazhen Huang, Xu Jiang, Li Lu, Jingyan Jiang, Zhi Wang

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 1 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 L_NC feature-classifier alignment loss to entropy minimization (ablation)Tent/entropy baseline · ImageNet-C (ViT-B/16)avg accuracy: 51.13 -> 53.17Improved
add L_NC feature-classifier alignment loss to entropy minimization (ablation)Tent/entropy baseline · CIFAR-10-C (ResNet50)avg accuracy: 75.19 -> 75.31Improved
add L_NC to entropy loss with filtering and dynamic weight (ablation)NCTTA · ImageNet-C (ViT-B/16)avg accuracy: 53.97 -> 66.50Improved
add L_NC to entropy loss with filtering and dynamic weight (ablation)NCTTA · CIFAR-10-C (ResNet50)avg accuracy: 76.87 -> 78.10Improved
use hybrid targets (tuned alpha, k) instead of pseudo-label only (ablation)NCTTA · ImageNet-C Contrast severity 5accuracyImproved
choose InfoNCE-style vs L2 or Triplet L_NC (ablation)NCTTA · CIFAR-10-C / ImageNet-Cavg accuracyMixed
use NCTTA instead of TentNCTTA · ImageNet-C CTTAavg accuracy: 66.27 -> 71.27Improved
use NCTTA instead of TentNCTTA · ImageNet-C batch size 1avg accuracy: 49.19 -> 59.69Improved
use NCTTA instead of DeYONCTTA · Waterbirdsworst-group accuracy: 75.65 -> 76.56No clear effect
use NCTTA instead of DeYONCTTA · PACSavg accuracy: 76.67 -> 77.36Improved
apply Tent adaptation to snow and frost corruptionsTent · ImageNet-C (ViT-B/16)accuracy: 22.15 -> 17.33 (Snow)Hurt

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