AI Paper Atlas

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

Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon, KUK-JIN YOON

ECCV 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 0 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 DO-ALLEATA · ImageNet-Cavg error (%): 58.0 -> 56.6Improved
add DO-ALLRMT · ImageNet-Cavg error (%): 59.8 -> 57.4Improved
add DO-ALLROID · ImageNet-Cavg error (%): 54.5 -> 53.6Improved
add DO-ALLASR · ImageNet-Cavg error (%): 54.3 -> 53.7Improved
add DO-ALLROID · CCC (Hard)accuracy (%): 13.2 -> 15.5Improved
add DO-ALLROID · CCC (average)accuracy (%): 33.6 -> 34.7Improved
add harm-adaptive blending (ablation)DO-ALL (Replay+MMD+MixUp) · ImageNet-C (ROID)avg error (%): 54.0 -> 53.6Improved
combine Replay, MMD and MixUp (ablation)ROID · ImageNet-Cavg error (%): 54.5 -> 54.0Improved
use Target-Anchor MixUp instead of no MixUp (ablation)DO-ALL · ImageNet-C (ROID)avg error (%): 53.77 -> 53.55Improved
use Target-Target MixUp instead of Target-Anchor (ablation)DO-ALL · ImageNet-C (ROID)avg error (%): 53.55 -> 53.68Hurt
assign nearest anchor instead of farthest (ablation)RMT + DO-ALL · ImageNet-Cavg error (%): 61.9 -> 57.4Improved
use SRe2L, DELT or WMDD for anchor distillation (ablation)ROID + DO-ALL · ImageNet-Cavg error (%): 53.7 / 53.6 / 53.6No clear effect

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