Skip to content
AI Atlas
PaperActive

Distilling Image Prototypes for Guided Test-Time Adaptation

arxiv.org/abs/2609.09737

Updated 50 min ago · first seen 11 Sept 2026

paper_01M294GMN772CV99QQC8ZFXEGG

Published
11 Sept 2026
T1 · 50 min ago
arXiv
2609.09737
T1 · 50 min ago
Category
cs.CV
T1 · 50 min ago

Abstract

Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from noisy pseudo-labels and catastrophic forgetting of source knowledge. Uncertainty-based approaches designed to mitigate error accumulation often yield overconfident or computationally expensive estimates, while strategies intended to prevent forgetting via prototype replay rely on static representations that easily become misaligned as the model adapts. To address these issues, this paper proposes a novel framework, Distilling Image Prototype for Guided Test-Time Adaptation (DIPTTA). The core of the proposed approach is the introduction of a Distill Image Prototype (DIP), a compact set of synthetic images that serves as a dynamic and regenerative anchor of source knowledge. This prototype enables a dynamic feature replay mechanism that continuously generates feature prototypes aligned with the current state of the model, thus effectively preventing catastrophic forgetting. Furthermore, the DIP anchors a source-calibrated uncertainty estimation method, which provides a less biased measure of sample reliability by leveraging stable source knowledge, thereby robustly suppressing error accumulation. Extensive experiments on multiple benchmarks demonstrate that DIPTTA significantly outperforms state-of-the-art methods, particularly under severe domain shifts. The source code is available at https://github.com/LiwenWang919/DIPTTA.

Authors 7

Liwen Wang, Xingbo Dong, Iman Yi Liao, Deyin Liu, Massimo Tistarelli, Lin Yuanbo Wu, Zhe Jin

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

arXiv id
2609.09737

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Categories
cs.CV, cs.AI

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Primary category
cs.CV

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

50 min ago

Conflicts

None