{"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/everything-to-the-synthetic-diffusion-driven","title":"Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment","arxiv_id":"2406.04295","date":"2024-06-06","proceeding":"CVPR 2025 1","authors":["Jiayi Guo","Junhao Zhao","Chaoqun Du","Yulin Wang","Chunjiang Ge","Zanlin Ni","Shiji Song","Humphrey Shi","Gao Huang"],"abstract":"Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model performance sensitive to the amount and order of target data. The recently proposed diffusion-driven TTA methods mitigate this by adapting model inputs instead of weights, where an unconditional diffusion model, trained on the source domain, transforms target-domain data into a synthetic domain that is expected to approximate the source domain. However, in this paper, we reveal that although the synthetic data in diffusion-driven TTA seems indistinguishable from the source data, it is unaligned with, or even markedly different from the latter for deep networks. To address this issue, we propose a \\textbf{S}ynthetic-\\textbf{D}omain \\textbf{A}lignment (SDA) framework. Our key insight is to fine-tune the source model with synthetic data to ensure better alignment. Specifically, we first employ a conditional diffusion model to generate labeled samples, creating a synthetic dataset. Subsequently, we use the aforementioned unconditional diffusion model to add noise to and denoise each sample before fine-tuning. This Mix of Diffusion (MoD) process mitigates the potential domain misalignment between the conditional and unconditional models. Extensive experiments across classifiers, segmenters, and multimodal large language models (MLLMs, \\eg, LLaVA) demonstrate that SDA achieves superior domain alignment and consistently outperforms existing diffusion-driven TTA methods. Our code is available at https://github.com/SHI-Labs/Diffusion-Driven-Test-Time-Adaptation-via-Synthetic-Domain-Alignment.","url_abs":"https://arxiv.org/abs/2406.04295v2","url_pdf":"https://arxiv.org/pdf/2406.04295v2.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":"everything-to-the-synthetic-diffusion-driven","repo_url":"https://github.com/shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04295"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment","reach":{"status":"ok"}}],"summary":{"ran_fixture":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"076fb2e4d08e8e8d","entry":"fuse_img_from_logits","repo":"shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment","repo_kind":"official","path":"eval/evaluation.py","file_url":"https://github.com/shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment/blob/HEAD/eval/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"076fb2e4d08e8e8d"}},{"code_sha256_prefix":"66478fed3d5168c0","entry":"select_logits_to_idx","repo":"shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment","repo_kind":"official","path":"eval/evaluation.py","file_url":"https://github.com/shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment/blob/HEAD/eval/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66478fed3d5168c0"}},{"code_sha256_prefix":"b99fc6b8a3e24879","entry":"tackle_img_from_idx","repo":"shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment","repo_kind":"official","path":"eval/evaluation.py","file_url":"https://github.com/shi-labs/diffusion-driven-test-time-adaptation-via-synthetic-domain-alignment/blob/HEAD/eval/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99fc6b8a3e24879"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}