Browse State-of-the-Art › Unsupervised Domain Adaptation

Unsupervised Domain Adaptation

864 papers with code · 49 benchmarks · 34 datasets archive 2025-07-28

Computer VisionMethodology

Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.

Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

49 leaderboard tables shown for this task, 49 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 49 until expanded.

Syntology 5 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): SYNTHIA-to-Cityscapes (1 judged, 0 placed), GTAV-to-Cityscapes Labels (1 judged, 0 placed), Office-Home (2 judged, 0 placed), VisDA2017 (1 judged, 0 placed), Office-31 (1 judged, 0 placed), DomainNet (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Duke to Market (26 rows) CORE-ReID CORE-ReID: Comprehensive Optimization and Refinement through... code — Compare
Market to Duke (25 rows) CORE-ReID CORE-ReID: Comprehensive Optimization and Refinement through... code — Compare
SYNTHIA-to-Cityscapes (23 rows) DCF Transferring to Real-World Layouts: A Depth-aware Framework for... code — Compare
Cityscapes to Foggy Cityscapes (22 rows) ALDI++(Resnet50+FPN) — — — Compare
GTAV-to-Cityscapes Labels (20 rows) MIC MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation code — Compare
Office-Home (20 rows) FFTAT Feature Fusion Transferability Aware Transformer for Unsupervised... code — Compare
Market to MSMT (17 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
ImageNet-C (16 rows) EfficientNet-L2+RPL If your data distribution shifts, use self-learning code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
VehicleID to VeRi-776 (14 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
Duke to MSMT (13 rows) CORE-ReID CORE-ReID: Comprehensive Optimization and Refinement through... code — Compare
SIM10K to Cityscapes (13 rows) ALDI++ Align and Distill: Unifying and Improving Domain Adaptive Object Detection code — Compare
Veri-776 to VehicleID Medium (13 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
Veri-776 to VehicleID Large (13 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
VisDA2017 (13 rows) FFTAT Feature Fusion Transferability Aware Transformer for Unsupervised... code — Compare
CUHK03 to Market (9 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
VehicleID to VERI-Wild Small (9 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
VehicleID to VERI-Wild Medium (9 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
VehicleID to VERI-Wild Large (9 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
ImageNet-R (8 rows) Model soups (ViT-G/14) Model soups: averaging weights of multiple fine-tuned models... code Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified Compare
Market to CUHK03 (8 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
Veri-776 to VehicleID Small (8 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
CUHK03 to MSMT (7 rows) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
CFC-DAOD (6 rows) ALDI++ (ResNet50-FPN) Align and Distill: Unifying and Improving Domain Adaptive Object Detection code — Compare
HMDB-UCF (6 rows) TranSVAE — — — Compare
UCF-HMDB (6 rows) TranSVAE — — — Compare
EPIC-KITCHENS-100 (5 rows) TranSVAE — — — Compare
Jester (Gesture Recognition) (5 rows) TranSVAE — — — Compare
Office-31 (5 rows) PMTrans Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game... — — Compare
Office-Home (RS-UT imbalance) (5 rows) Implicit Alignment (with MDD) Implicit Class-Conditioned Domain Alignment for Unsupervised... code — Compare
BDD100k to Cityscapes (4 rows) RT-DATR(real-time, 640x640,R-34) RT-DATR:Real-time Unsupervised Domain Adaptive Detection... code — Compare
Cityscapes-to-OxfordCar (4 rows) Uncertainty + Adaboost Adaptive Boosting for Domain Adaptation: Towards Robust... code — Compare
DomainNet (4 rows) SAMB Semantic-aware Message Broadcasting for Efficient Unsupervised... code — Compare
virtual KITTI to KITTI (MDE) (4 rows) CoReg Consistency Regularisation for Unsupervised Domain Adaptation in... code — Compare
PACS (3 rows) CoVi Contrastive Vicinal Space for Unsupervised Domain Adaptation code — Compare
SIM10K to BDD100K (3 rows) DDT Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector code — Compare
Kitti to Cityscapes (2 rows) RT-DATR(real-time, 640x640) RT-DATR:Real-time Unsupervised Domain Adaptive Detection... code — Compare
OOD-CV (2 rows) 3DUDA Source-Free and Image-Only Unsupervised Domain Adaptation for... — — Compare
Pascal VOC to Clipart1K (2 rows) DDT Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector code — Compare
PreSIL to KITTI (2 rows) PointDAN PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud... code — Compare
ClonedPerson (1 row) SpCL Cloning Outfits from Real-World Images to 3D Characters for... code — Compare
FHIST (1 row) CHATTY+MCC CHATTY: Coupled Holistic Adversarial Transport Terms with Yield... — — Compare
GTA5+Synscapes+Urbansyn to Cityscapes (1 row) Co-Training All for One, and One for All: UrbanSyn Dataset, the third... — — Compare
GTA5-to-Cityscapes (1 row) CLUDA+HRDA CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for... code — Compare
ImageNet-A (1 row) EfficientNet-L2 NoisyStudent + RPL If your data distribution shifts, use self-learning code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
MSCOCO to FLIR ADAS (1 row) SGADA Self-training Guided Adversarial Domain Adaptation For Thermal Imagery code — Compare
Portraits (over time) (1 row) Gradual Self-Training (Small Conv) Understanding Self-Training for Gradual Domain Adaptation code — Compare
UDA-CH (1 row) DA-RetinaNet An Unsupervised Domain Adaptation Scheme for Single-Stage Artwork... code — Compare
Vehicle to VERI-Wild (1 row) CORE-ReID V2 CORE-ReID V2: Advancing the Domain Adaptation for Object... code — Compare
VisDA-2017 (1 row) TransAdapter TransAdapter: Vision Transformer for Feature-Centric Unsupervised... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

34 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 34 until expanded.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,951 · with a code link: 864 · where Syntology ran a sample: 200 (174 with a run with no instrument failure, 26 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (200 of 1,951 tagged: 174 with a run with no instrument failure, 26 where every run was a failure of Syntology's instrument)

Page 1 of 20: papers 1 to 100 of 1,951, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 49 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections