{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/mecta-memory-economic-continual-test-time","title":"MECTA: Memory-Economic Continual Test-Time Model Adaptation","arxiv_id":null,"date":"2023-02-01","proceeding":"ICLR 2023 2","authors":["Junyuan Hong","Lingjuan Lyu","Jiayu Zhou","Michael Spranger"],"abstract":"Continual Test-time Adaptation (CTA) is a promising art to secure accuracy gains in continually-changing environments. The state-of-the-art adaptations improve out-of-distribution model accuracy via computation-efficient online test-time gradient descents but meanwhile cost about times of memory versus the inference, even if only a small portion of parameters are updated. Such high memory consumption of CTA substantially impedes wide applications of advanced CTA on memoryconstrained devices. In this paper, we provide a novel solution, dubbed MECTA, to drastically improve the memory efficiency of gradient-based CTA. Our profiling\r\nshows that the major memory overhead comes from the intermediate cache for backpropagation, which scales by the batch size, channel, and layer number. Therefore, we propose to reduce batch sizes, adopt an adaptive normalization layer to maintain\r\nstable and accurate predictions, and stop the back-propagation caching heuristically. On the other hand, we prune the networks to reduce the computation and memory overheads in optimization and recover the parameters afterward to avoid forgetting. The proposed MECTA is efficient and can be seamlessly plugged into state-of-theart CTA algorithms at negligible overhead on computation and memory. On three datasets, CIFAR10, CIFAR100, and ImageNet, MECTA improves the accuracy by at least 6% with constrained memory and significantly reduces the memory costs of ResNet50 on ImageNet by at least 70% with comparable accuracy. Our codes can be accessed at https://github.com/SonyAI/MECTA.","url_abs":"https://openreview.net/forum?id=N92hjSf5NNh","url_pdf":"https://openreview.net/pdf?id=N92hjSf5NNh","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mecta-memory-economic-continual-test-time","repo_url":"https://github.com/sonyai/mecta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"mecta-memory-economic-continual-test-time","repo_url":"https://github.com/SonyResearch/MECTA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"sonyai/mecta","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SonyResearch/MECTA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f244eef39f1d195a0909f0f40e34cad0d066aa3b72cd4e8183f803020ba024c1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}