Papers › SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain Generalizable...

SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain Generalizable Representation Learning

5 Dec 2024arXiv:2412.04077archive 2025-07-28

Seokju Yun, Seunghye Chae, Dongheon Lee, Youngmin Ro

Domain generalization (DG) aims to adapt a model using one or multiple source domains to ensure robust performance in unseen target domains. Recently, Parameter-Efficient Fine-Tuning (PEFT) of foundation models has shown promising results in the context of DG problem. Nevertheless, existing PEFT methods still struggle to strike a balance between preserving generalizable components of the pre-trained model and learning task-specific features. To gain insights into the distribution of generalizable components, we begin by analyzing the pre-trained weights through the lens of singular value decomposition. Building on these insights, we introduce Singular Value Decomposed Low-Rank Adaptation (SoRA), an approach that selectively tunes minor singular components while keeping the residual parts frozen. SoRA effectively retains the generalization ability of the pre-trained model while efficiently acquiring task-specific skills. Furthermore, we freeze domain-generalizable blocks and employ an annealing weight decay strategy, thereby achieving an optimal balance in the delicate trade-off between generalizability and discriminability. SoRA attains state-of-the-art results on multiple benchmarks that span both domain generalized semantic segmentation to domain generalized object detection. In addition, our methods introduce no additional inference overhead or regularization loss, maintain compatibility with any backbone or head, and are designed to be versatile, allowing easy integration into a wide range of tasks.

PaperPDFCode

Code

ysj9909/DG-SoRA officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationDomain GeneralizationObject DetectionRepresentation LearningSemantic Segmentationobject-detectionparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Cityscapes to ACDC SoRA mIoU 78.8 #1 of 16 Archive leaderboard report
Domain Generalization GTA-to-Avg(Cityscapes,BDD,Mapillary) SoRA mIoU 68.27 #1 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Weight Decay

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