Browse State-of-the-Art › Domain Generalization

Domain Generalization

859 papers with code · 21 benchmarks · 31 datasets archive 2025-07-28

Computer Vision

The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain

Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

21 leaderboard tables shown for this task, 21 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 21 until expanded.

Syntology 4 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): ImageNet-A (1 judged, 0 placed), DomainNet (1 judged, 0 placed), VLCS (1 judged, 0 placed), GTA5-to-Cityscapes (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
PACS (133 rows) SIMPLE+ SIMPLE: Specialized Model-Sample Matching for Domain Generalization code — Compare
VizWiz-Classification (90 rows) VOLO-D5 VOLO: Vision Outlooker for Visual Recognition code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
ImageNet-C (47 rows) DINOv2 (ViT-g/14, frozen model, linear eval) DINOv2: Learning Robust Visual Features without Supervision code Syntology community repositories only · 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified Compare
Office-Home (45 rows) MoA (OpenCLIP, ViT-B/16) Domain Generalization Using Large Pretrained Models with... code — Compare
ImageNet-A (39 rows) Model soups (BASIC-L) 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
ImageNet-R (39 rows) Model soups (BASIC-L) 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
DomainNet (38 rows) L2C (CLIP, ViT-L/14) Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation code — Compare
VLCS (37 rows) CAR-FT (CLIP, ViT-B/16) Context-Aware Robust Fine-Tuning — — Compare
TerraIncognita (30 rows) UniDG + CORAL + ConvNeXt-B Towards Unified and Effective Domain Generalization code — Compare
GTA-to-Avg(Cityscapes,BDD,Mapillary) (24 rows) SoRA SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain... code — Compare
ImageNet-Sketch (20 rows) Model soups (BASIC-L) 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
GTA5-to-Cityscapes (8 rows) tqdm (EVA02-CLIP-L) Textual Query-Driven Mask Transformer for Domain Generalized Segmentation code — Compare
NICO Animal (5 rows) NAS-OoD NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization code Syntology 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified Compare
NICO Vehicle (5 rows) NAS-OoD NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization code Syntology 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified Compare
Stylized-ImageNet (3 rows) MAE+DAT (ViT-H) Enhance the Visual Representation via Discrete Adversarial Training code Syntology official (archive's flag): 9 ran · 10 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
Rotated Fashion-MNIST (2 rows) MatchDG Domain Generalization using Causal Matching code Syntology official: no sample here; runs from other or unrecorded repositories · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified Compare
CIFAR-100C (1 row) GLOT-DR Global-Local Regularization Via Distributional Robustness code — Compare
CIFAR-10C (1 row) GLOT-DR Global-Local Regularization Via Distributional Robustness code — Compare
Cityscapes to ACDC (1 row) ADSI Domain Generalization through Attenuation of Domain-Specific Information code — Compare
LipitK (1 row) CSD (Ours) Efficient Domain Generalization via Common-Specific Low-Rank Decomposition code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified Compare
WildDash (1 row) ITEN Exploiting Image Translations via Ensemble Self-Supervised... — — 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

31 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 31 until expanded.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,751 · with a code link: 859 · where Syntology ran a sample: 271 (227 with a run with no instrument failure, 44 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (271 of 1,751 tagged: 227 with a run with no instrument failure, 44 where every run was a failure of Syntology's instrument)

Page 1 of 18: papers 1 to 100 of 1,751, 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 64 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