{"url":"/dataset/domainnet","name":"DomainNet","full_name":"DomainNet","description_markdown":"**DomainNet** is a dataset of common objects in six different domain. All domains include 345 categories (classes) of objects such as Bracelet, plane, bird and cello. The domains include clipart: collection of clipart images; real: photos and real world images; sketch: sketches of specific objects; infograph: infographic images with specific object; painting artistic depictions of objects in the form of paintings and quickdraw: drawings of the worldwide players of game “Quick Draw!”.\r\n\r\nSource: [What is being transferred in transfer learning?](https://arxiv.org/abs/2008.11687)\r\nImage Source: [http://ai.bu.edu/M3SDA/](http://ai.bu.edu/M3SDA/)","description_withheld":null,"homepage":"http://ai.bu.edu/M3SDA/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/moment-matching-for-multi-source-domain","title":"Moment Matching for Multi-Source Domain Adaptation","first_author":"Xingchao Peng","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"http://ai.bu.edu/M3SDA/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"Domain Generalization","url":"/task/domain-generalization","datasets_with_task":"/datasets/task/domain-generalization"},{"name":"Multi-Source Unsupervised Domain Adaptation","url":"/task/multi-source-unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/multi-source-unsupervised-domain-adaptation"},{"name":"Partial Domain Adaptation","url":"/task/partial-domain-adaptation","datasets_with_task":"/datasets/task/partial-domain-adaptation"},{"name":"Universal Domain Adaptation","url":"/task/universal-domain-adaptation","datasets_with_task":"/datasets/task/universal-domain-adaptation"},{"name":"Multi-target Domain Adaptation","url":"/task/multi-target-domain-adaptation","datasets_with_task":"/datasets/task/multi-target-domain-adaptation"},{"name":"Blended-target Domain Adaptation","url":"/task/blended-target-domain-adaptation","datasets_with_task":"/datasets/task/blended-target-domain-adaptation"},{"name":"Unsupervised Continual Domain Shift Learning","url":"/task/unsupervised-continual-domain-shift-learning","datasets_with_task":"/datasets/task/unsupervised-continual-domain-shift-learning"},{"name":"Zero-Shot Learning + Domain Generalization","url":"/task/zero-shot-learning-domain-generalization","datasets_with_task":"/datasets/task/zero-shot-learning-domain-generalization"}],"languages":[],"variants":["DomainNet"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/domainnet-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/domainnet","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":753,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset_variant":"DomainNet","rows":38,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"L2C (CLIP, ViT-L/14)","paper":"/paper/learning-to-adapt-frozen-clip-for-few-shot","metrics":{"Average Accuracy":"67.4"},"code_links":[{"title":"chi-chi-zx/L2C","url":"https://github.com/chi-chi-zx/L2C"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/universal-domain-adaptation-on-domainnet","task":"Universal Domain Adaptation","dataset_variant":"DomainNet","rows":12,"metrics":["H-Score","Source-free"],"first_row_in_archive_order":{"model":"TASC","paper":"/paper/target-semantics-clustering-via-text-1","metrics":{"H-Score":"73.28","Source-free":"no"},"code_links":[{"title":"Sapphire-356/TASC","url":"https://github.com/Sapphire-356/TASC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/domain-adaptation-on-domainnet-1","task":"Domain Adaptation","dataset_variant":"DomainNet","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SPM","paper":"/paper/shuffle-patchmix-augmentation-with-confidence","metrics":{"Accuracy":"71.1"},"code_links":[{"title":"PrasannaPulakurthi/SPM","url":"https://github.com/PrasannaPulakurthi/SPM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-target-domain-adaptation-on-domainnet","task":"Multi-target Domain Adaptation","dataset_variant":"DomainNet","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MCDA","paper":"/paper/class-overwhelms-mutual-conditional-blended","metrics":{"Accuracy":"34.5"},"code_links":[{"title":"Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-domainnet-1","task":"Unsupervised Domain Adaptation","dataset_variant":"DomainNet","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SAMB","paper":"/paper/semantic-aware-message-broadcasting-for","metrics":{"Accuracy":"49.8"},"code_links":[{"title":"lixinustc/samb-transformeruda","url":"https://github.com/lixinustc/samb-transformeruda"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/partial-domain-adaptation-on-domainnet","task":"Partial Domain Adaptation","dataset_variant":"DomainNet","rows":3,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"AR","paper":"/paper/adversarial-reweighting-for-partial-domain","metrics":{"Accuracy (%)":"65.76"},"code_links":[{"title":"xjtu-xgu/adversarial-reweighting-for-partial-domain-adaptation","url":"https://github.com/xjtu-xgu/adversarial-reweighting-for-partial-domain-adaptation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/blended-target-domain-adaptation-on-domainnet","task":"Blended-target Domain Adaptation","dataset_variant":"DomainNet","rows":2,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"MCDA","paper":"/paper/class-overwhelms-mutual-conditional-blended","metrics":{"Average Accuracy":"34.5"},"code_links":[{"title":"Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/target-semantics-clustering-via-text-1","title":"Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation","date":"2025-06-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shuffle-patchmix-augmentation-with-confidence","title":"Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation","date":"2025-05-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-to-adapt-frozen-clip-for-few-shot","title":"Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation","date":"2025-01-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/transadapter-vision-transformer-for-feature","title":"TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation","date":"2024-12-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adapting-to-distribution-shift-by-visual","title":"Adapting to Distribution Shift by Visual Domain Prompt Generation","date":"2024-05-05","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/soft-prompt-generation-for-domain","title":"Soft Prompt Generation for Domain Generalization","date":"2024-04-30","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sf-da-2-source-free-domain-adaptation-through","title":"SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation","date":"2024-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lead-learning-decomposition-for-source-free","title":"LEAD: Learning Decomposition for Source-free Universal Domain Adaptation","date":"2024-03-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-multi-domain-generalization-with-a","title":"Rethinking Multi-domain Generalization with A General Learning Objective","date":"2024-02-29","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/combining-inherent-knowledge-of-vision","title":"Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance","date":"2023-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/domain-generalization-using-large-pretrained","title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","date":"2023-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-unified-and-effective-domain","title":"Towards Unified and Effective Domain Generalization","date":"2023-10-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/distilling-from-vision-language-models-for","title":"Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification","date":"2023-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":12,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/promptstyler-prompt-driven-style-generation","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","date":"2023-07-27","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/poem-polarization-of-embeddings-for-domain","title":"POEM: Polarization of Embeddings for Domain-Invariant Representations","date":"2023-05-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":9,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simple-specialized-model-sample-matching-for","title":"SIMPLE: Specialized Model-Sample Matching for Domain Generalization","date":"2023-05-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/universal-domain-adaptation-via-compressive","title":"Universal Domain Adaptation via Compressive Attention Matching","date":"2023-04-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/patch-mix-transformer-for-unsupervised-domain","title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","date":"2023-03-23","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/upcycling-models-under-domain-and-category","title":"Upcycling Models under Domain and Category Shift","date":"2023-03-13","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/class-overwhelms-mutual-conditional-blended","title":"Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation","date":"2023-02-03","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/padclip-pseudo-labeling-with-adaptive","title":"PADCLIP: Pseudo-labeling with Adaptive Debiasing in CLIP for Unsupervised Domain Adaptation","date":"2023-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/boosting-novel-category-discovery-over-1","title":"Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-aware-message-broadcasting-for","title":"Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation","date":"2022-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-robust-fine-tuning","title":"Context-Aware Robust Fine-Tuning","date":"2022-11-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unified-optimal-transport-framework-for","title":"Unified Optimal Transport Framework for Universal Domain Adaptation","date":"2022-10-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/meta-dmoe-adapting-to-domain-shift-by-meta","title":"Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts","date":"2022-10-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sparse-fusion-mixture-of-experts-are-domain","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","date":"2022-06-08","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":7,"samples_unverified":7,"pointer_only_for_licence":14,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynamic-domain-generalization","title":"Dynamic Domain Generalization","date":"2022-05-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cadg-a-model-based-on-cross-attention-for","title":"CADG: A Model Based on Cross Attention for Domain Generalization","date":"2022-03-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/domain-generalization-by-mutual-information","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","date":"2022-03-21","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":11,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/domain-generalization-using-pretrained-models","title":"Domain Generalization using Pretrained Models without Fine-tuning","date":"2022-03-09","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/umad-universal-model-adaptation-under-domain","title":"UMAD: Universal Model Adaptation under Domain and Category Shift","date":"2021-12-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adaptive-methods-for-aggregated-domain","title":"Adaptive Methods for Aggregated Domain Generalization","date":"2021-12-09","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-reweighting-for-partial-domain","title":"Adversarial Reweighting for Partial Domain Adaptation","date":"2021-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ensemble-of-averages-improving-model","title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","date":"2021-10-21","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fishr-invariant-gradient-variances-for-out-of","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","date":"2021-09-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/domain-consensus-clustering-for-universal","title":"Domain Consensus Clustering for Universal Domain Adaptation","date":"2021-06-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ovanet-one-vs-all-network-for-universal","title":"OVANet: One-vs-All Network for Universal Domain Adaptation","date":"2021-04-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/curriculum-graph-co-teaching-for-multi-target","title":"Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation","date":"2021-04-01","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/domain-generalization-needs-stochastic-weight","title":"SWAD: Domain Generalization by Seeking Flat Minima","date":"2021-02-17","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-balance-specificity-and","title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","date":"2020-08-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-to-detect-open-classes-for-universal","title":"Learning to Detect Open Classes for Universal Domain Adaptation","date":"2020-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-balanced-and-uncertainty-aware-approach-for","title":"A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation","date":"2020-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/do-we-really-need-to-access-the-source-data","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","date":"2020-02-20","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/less-confusion-more-transferable-minimum","title":"Minimum Class Confusion for Versatile Domain Adaptation","date":"2019-12-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/universal-domain-adaptation","title":"Universal Domain Adaptation","date":"2019-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/domain-agnostic-learning-with-disentangled","title":"Domain Agnostic Learning with Disentangled Representations","date":"2019-04-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/partial-adversarial-domain-adaptation","title":"Partial Adversarial Domain Adaptation","date":"2018-08-10","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":23,"samples_harvested":155,"samples_ran":84,"samples_unverified":71,"pointer_only_for_licence":53,"papers_with_no_sample_that_ran":5,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}