Return of Frustratingly Easy Unsupervised Video Domain Adaptation

Pengfei Wei; Yiqun Sun; Zhiqiang Xu; Yiping Ke; Lawrence B. Hsieh

cs.CVMay 19, 2026

Return of Frustratingly Easy Unsupervised Video Domain Adaptation

Authors: Pengfei Wei, Yiqun Sun, Zhiqiang Xu, Yiping Ke, Lawrence B. Hsieh

Organizations: 1Magellan Technology Research Institute (MTRI), Japan · 2Mohamed bin Zayed University of Artificial Intelligence, UAE · 3Nanyang Technological University, Singapore.

Abstract

Unsupervised video domain adaptation (UVDA) is a practical but under-explored problem. In this paper, we propose a frustratingly easy UVDA method, called MetaTrans. Specifically, MetaTrans adopts a concise learning objective that contains only two fundamental loss terms. Despite the simplicity of the learning objective, MetaTrans embodies an advanced UVDA idea, that is, handling the spatial and temporal divergence of cross-domain videos separately, through a subtle model architecture design. By implementing a temporal-static subtraction module, MetaTrans effectively removes spatial and temporal divergence. Extensive empirical evaluations, particularly on various cross-domain action recognition tasks, show substantial absolute adaptation performance enhancement and significantly superior relative performance gain compared with state-of-the-art UVDA baselines.

Explore similar work

Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts
Jul 27, 2026André Sacilotti, Samuel Felipe dos Santos, Jurandy AlmeidaOpen-Vocabulary Action Recognition Videos
Variance-reduced Domain Adaptation using Paired Sampling
Jul 22, 2026Andrea NapoliDomain Adaptation Variance Reduction
CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation
Jul 11, 2026Zhimin Yuan, Ming Cheng, Shangshu Yu +43D Semantic Segmentation Domain Adaptation

Jul 27, 2026 · cs.CVJ/K move · Enter open · S save

Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts

André Sacilotti, Samuel Felipe dos Santos, Jurandy Almeida

University of São Paulo São Carlos, São Paulo, Brazil · Federal University of São Carlos Sorocaba, São Paulo, Brazil

Deep learning models have achieved state-of-the-art performance in several computer vision tasks. However, they experience severe performance degradation when applied to real-world scenarios due to unanticipated distribution shifts. Test-Time Adaptation (TTA) attempts to solve this problem by using unlabeled data from the target domain to dynamically adapt to the test distribution at inference time, without access to the source data. However, TTA remains a challenging problem when adapting to continuous, temporally correlated data, such as videos, and in scenarios where the target domain contains severe domain shifts. For this reason, few works in the literature explore TTA for videos under such extreme conditions. To overcome these limitations, we propose Test-time Adaptation via Dual Distillation (TADD), an online adaptation framework that relies on a lightweight projection adapter to bridge the domain gap. The adapter module is pre-trained on the source domain and then adapted to the target using our proposed complementary losses: (i) zero-shot distillation, which encourages alignment with the domain-agnostic features from a pre-trained vision-language model (VLM); and (ii) target distillation, which retains the source domain discriminative knowledge encoded in the pre-trained adapter. Built upon a frozen CLIP backbone, our method introduces this lightweight projection adapter as the sole updatable component during inference. We conducted extensive evaluations on three well-known video action recognition benchmarks: UCF-HMDB, Daily-DA, and Sports-DA. Our experiments in the closed-set scenario demonstrate that our method consistently outperforms state-of-the-art TTA baselines. Notably, our TTA approach improves upon previous methods by up to +3.81% on UCF-HMDB, +2.63% on Daily-DA, and +3.03% on Sports-DA.

Open-Vocabulary Action Recognition Videos Distribution Shifts Large Vision Language Models

Open paper Ask about it PDF

Abstract

Explore similar work

Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts

Variance-reduced Domain Adaptation using Paired Sampling

CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation