{"ID":2839476,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15276","arxiv_id":"2511.15276","title":"SNAP: Low-Latency Test-Time Adaptation with Sparse Updates","abstract":"Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, making them unsuitable for resource-constrained edge environments. To address this, we propose SNAP, a sparse TTA framework that reduces adaptation frequency and data usage while preserving accuracy. SNAP maintains competitive accuracy even when adapting based on only 1% of the incoming data stream, demonstrating its robustness under infrequent updates. Our method introduces two key components: (i) Class and Domain Representative Memory (CnDRM), which identifies and stores a small set of samples that are representative of both class and domain characteristics to support efficient adaptation with limited data; and (ii) Inference-only Batch-aware Memory Normalization (IoBMN), which dynamically adjusts normalization statistics at inference time by leveraging these representative samples, enabling efficient alignment to shifting target domains. Integrated with five state-of-the-art TTA algorithms, SNAP reduces latency by up to 93.12%, while keeping the accuracy drop below 3.3%, even across adaptation rates ranging from 1% to 50%. This demonstrates its strong potential for practical use on edge devices serving latency-sensitive applications. The source code is available at https://github.com/chahh9808/SNAP.","short_abstract":"Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, making them unsuitable for resource-constrained edge environments. To address this, we propose SNAP, a sparse TTA framework that r...","url_abs":"https://arxiv.org/abs/2511.15276","url_pdf":"https://arxiv.org/pdf/2511.15276v1","authors":"[\"Hyeongheon Cha\",\"Dong Min Kim\",\"Hye Won Chung\",\"Taesik Gong\",\"Sung-Ju Lee\"]","published":"2025-11-19T09:40:24Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":606877,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839476,"paper_url":"https://arxiv.org/abs/2511.15276","paper_title":"SNAP: Low-Latency Test-Time Adaptation with Sparse Updates","repo_url":"https://github.com/chahh9808/SNAP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}