Browse State-of-the-Art › Single-Source Domain Generalization
Single-Source Domain Generalization
26 papers with code · 2 benchmarks · 1 dataset archive 2025-07-28
In this task a model is trained in a single source domain and then it is tested in a number of target domains
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| PACS (10 rows) | Crafting-Shifts(ResNet18) | Crafting Distribution Shifts for Validation and Training in Single... | code | — | Compare |
| Digits-five (7 rows) | Crafting-Shifts(LeNet) | Crafting Distribution Shifts for Validation and Training in Single... | 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
1 dataset whose archive record lists this task, ordered by the archive's paper count.
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: 48 · with a code link: 26 · where Syntology ran a sample: 5 (5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 48 tagged: 5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 48 of 48, 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.
-
25 Oct 2019 3 repositories listedConvolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift.
-
20 Jan 2025 2 repositories listedInitially, we analyze the weak robustness of existing SEI methods from the perspective of the “shortcut learning” phenomenon in DL.
-
20 Apr 2021 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples)However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs.
-
29 May 2025 1 repository listedTo address this limitation, we propose Pseudo Multi-source Domain Generalization (PMDG), a novel framework that enables the application of sophisticated MDG algorithms in more practical Single-source Domain…
-
17 Mar 2025 1 repository listed 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) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Despite domain generalization (DG) has significantly addressed the performance degradation of pre-trained models caused by domain shifts, it often falls short in real-world deployment.
-
11 Feb 2025 1 repository listedIn this work, we propose two novel techniques to enhance generalization: dynamic color image normalization (DCIN) module and color-quality generalization (CQG) loss.
-
7 Nov 2024 1 repository listedSingle-source domain generalization (SDG) aims to learn a model from a single source domain that can generalize well on unseen target domains.
-
29 Sep 2024 1 repository listedThe method that achieves the best performance on the augmented validation is selected from the proposed family.
-
19 Sep 2024 1 repository listedIn this paper, we propose a novel Domain-Adaptive Prompt framework for fine-tuning the Segment Anything Model (termed as DAPSAM) to address single-source domain generalization (SDG) in segmenting medical images.
-
10 Sep 2024 1 repository listedDeploying deep segmentation models in new medical centers poses a significant challenge due to statistical disparities between source and unknown domains.
-
7 Sep 2024 1 repository listedThe proposed Random Amplitude Spectrum Synthesis for Single-Source Domain Generalization (RAS^4DG) is validated on 3D fetal brain images and 2D fundus photography, and achieves an improved DG segmentation performance…
-
2 May 2024 1 repository listedTo tackle domain shifts in data-scarce medical scenarios, we propose a Random frequency filtering enabled Single-source Domain Generalization algorithm (RaffeSDG), which promises robust out-of-domain inference with…
-
1 Apr 2024 1 repository listedIncorporating text features alongside visual features is a potential solution to enhance the model's understanding of the data, as it goes beyond pixel-level information to provide valuable context.
-
18 Mar 2024 1 repository listedThe task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets.
-
4 Jan 2024 1 repository listedDomain Generalization (DG) aims to reduce domain shifts between domains to achieve promising performance on the unseen target domain, which has been widely practiced in medical image segmentation.
-
18 Jul 2023 1 repository listed 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) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings.
-
18 Jul 2023 1 repository listedConsequently, domain generalization (DG) is developed to boost the performance of segmentation models on unseen domains.
-
10 Apr 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)Generally, a TTT strategy hinges its performance on two main factors: selecting an appropriate auxiliary TTT task for updating and identifying reliable parameters to update during the test phase.
-
27 Nov 2022 1 repository listedSingle-source domain generalization (SDG) in medical image segmentation is a challenging yet essential task as domain shifts are quite common among clinical image datasets.
-
25 Nov 2022 1 repository listedDomain generalization is the task of learning models that generalize to unseen target domains.
-
15 Jun 2022 1 repository listedTo be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies.
-
27 Apr 2022 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples)Generalizing visual recognition models trained on a single distribution to unseen input distributions (i. e. domains) requires making them robust to superfluous correlations in the training set.
-
1 Jan 2022 1 repository listedResearch has shown that convolutional neural networks for object recognition are vulnerable to changes in depiction because learning is biased towards the low-level statistics of texture patches.
-
1 Jan 2022 1 repository listedDomain Generalizable (DG) person ReID is a challenging task which trains a model on source domains yet generalizes well on target domains.
-
24 Nov 2021 1 repository listedIn this work, we investigate the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data is only available from one source domain…
-
26 Aug 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)Domain generalization (DG) aims to generalize a model trained on multiple source (i. e., training) domains to a distributionally different target (i. e., test) domain.
-
Dealing with the Evil Twins: Improving Random Augmentation by Addressing Catastrophic Forgetting of Diverse Augmentations9 Jun 2025 0 repositories listedData augmentation is a promising tool for enhancing out-of-distribution generalization, where the key is to produce diverse, challenging variations of the source domain via costly targeted augmentations that maximize…
-
PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization19 May 2025 0 repositories listedData augmentation is a popular tool for single source domain generalization, which expands the source domain by generating simulated ones, improving generalization on unseen target domains.
-
Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data12 Mar 2025 0 repositories listedAutomated knee cartilage segmentation using point-of-care ultrasound devices and deep-learning networks has the potential to enhance the management of knee osteoarthritis.
-
Rethinking domain generalization in medical image segmentation: One image as one domain8 Jan 2025 0 repositories listedDomain shifts in medical image segmentation, particularly when data comes from different centers, pose significant challenges.
-
Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification5 Dec 2024 0 repositories listed
-
TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction25 Nov 2024 0 repositories listed
-
DRIFTS: Optimizing Domain Randomization with Synthetic Data and Weight Interpolation for Fetal Brain Tissue Segmentation11 Nov 2024 0 repositories listed
-
Domain Expansion and Boundary Growth for Open-Set Single-Source Domain Generalization5 Nov 2024 0 repositories listed
-
Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification11 Oct 2024 0 repositories listed
-
Double Gradient Reversal Network for Single-Source Domain Generalization in Multi-mode Fault Diagnosis19 Jul 2024 0 repositories listed
-
FIESTA: Fourier-Based Semantic Augmentation with Uncertainty Guidance for Enhanced Domain Generalizability in Medical Image Segmentation20 Jun 2024 0 repositories listed
-
WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalization28 May 2024 0 repositories listed
-
Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection24 May 2024 0 repositories listed
-
HD Maps are Lane Detection Generalizers: A Novel Generative Framework for Single-Source Domain Generalization28 Nov 2023 0 repositories listed
-
CNN Feature Map Augmentation for Single-Source Domain Generalization26 May 2023 0 repositories listed
-
Frequency Decomposition to Tap the Potential of Single Domain for Generalization14 Apr 2023 0 repositories listed
-
7 Apr 2023 0 repositories listed
-
2 Apr 2023 0 repositories listed
-
1 Jan 2023 0 repositories listed
-
DGSS : Domain Generalized Semantic Segmentation using Iterative Style Mining and Latent Representation Alignment26 Feb 2022 0 repositories listed
-
1 Jan 2022 0 repositories listed
-
Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization15 Jun 2021 0 repositories listed
Syntology lines on 6 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