{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/vida-homeostatic-visual-domain-adapter-for","title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","arxiv_id":"2306.04344","date":"2023-06-07","proceeding":null,"authors":["Jiaming Liu","Senqiao Yang","Peidong Jia","Renrui Zhang","Ming Lu","Yandong Guo","Wei Xue","Shanghang Zhang"],"abstract":"Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and maintain the model plasticity, we design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Specifically, we first comprehensively explore the different domain representations of the adapters with trainable high-rank or low-rank embedding spaces. Then we inject ViDAs into the pre-trained model, which leverages high-rank and low-rank features to adapt the current domain distribution and maintain the continual domain-shared knowledge, respectively. To exploit the low-rank and high-rank ViDAs more effectively, we further propose a Homeostatic Knowledge Allotment (HKA) strategy, which adaptively combines different knowledge from each ViDA. Extensive experiments conducted on four widely used benchmarks demonstrate that our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Note that, our method can be regarded as a novel transfer paradigm for large-scale models, delivering promising results in adaptation to continually changing distributions. Project page: https://sites.google.com/view/iclr2024-vida/home.","url_abs":"https://arxiv.org/abs/2306.04344v3","url_pdf":"https://arxiv.org/pdf/2306.04344v3.pdf","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":"vida-homeostatic-visual-domain-adapter-for","repo_url":"https://github.com/yangsenqiao/vida","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vida-homeostatic-visual-domain-adapter-for","repo_url":"https://github.com/royzry98/moase-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.04344","atlas_url":"https://app.syntology.ai/?focus=2306.04344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04344"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/royzry98/moase-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangsenqiao/vida","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":3,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"63832452f78dcb58","entry":"collect_params","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/tent.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/tent.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63832452f78dcb58"}},{"code_sha256_prefix":"dae52c9027c48afd","entry":"forward_and_adapt","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/tent.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/tent.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dae52c9027c48afd"}},{"code_sha256_prefix":"108a82af5a25b36a","entry":"inject_trainable_vida","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/inject_vida.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/inject_vida.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"108a82af5a25b36a"}},{"code_sha256_prefix":"721e565ebd5fda4e","entry":"setup_source","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/imagenetc.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/imagenetc.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"721e565ebd5fda4e"}},{"code_sha256_prefix":"3078648c75e3e1e3","entry":"softmax_entropy","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/tent.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/tent.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3078648c75e3e1e3"}},{"code_sha256_prefix":"b8ea8e2ae9be86a9","entry":"softmax_entropy","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/vida.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/vida.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8ea8e2ae9be86a9"}},{"code_sha256_prefix":"a77d556c0aea19c1","entry":"update_ema_variables","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/cotta.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/cotta.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a77d556c0aea19c1"}},{"code_sha256_prefix":"f11bbc6fc4cc3fe7","entry":"update_ema_variables","repo":"yangsenqiao/vida","repo_kind":"official","path":"imagenet/vida.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/imagenet/vida.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f11bbc6fc4cc3fe7"}},{"code_sha256_prefix":"e589e47d748af885","entry":"softmax_entropy","repo":"yangsenqiao/vida","repo_kind":"official","path":"cifar/vida.py","file_url":"https://github.com/yangsenqiao/vida/blob/HEAD/cifar/vida.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e589e47d748af885"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}