Bi-Level Optimization for Single Domain Generalization

• URL: http://arxiv.org/abs/2604.06349v1
• Date: Tue, 07 Apr 2026 18:28:42 GMT
• Title: Bi-Level Optimization for Single Domain Generalization
• Abstract summary: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, is a challenge in machine learning.<n>We propose BiSDG, a bi-level optimization framework that explicitly decouples task learning from domain modeling.<n>BiSDG consistently outperforms prior methods, setting new state-of-the-art performance in the Single Domain Generalization setting.
• Score: 27.034057724775536
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains a fundamental challenge in robust machine learning. We address this underexplored setting, known as Single Domain Generalization (SDG), by proposing BiSDG, a bi-level optimization framework that explicitly decouples task learning from domain modeling. BiSDG simulates distribution shifts through surrogate domains constructed via label-preserving transformations of the source data. To capture domain-specific context, we propose a domain prompt encoder that generates lightweight modulation signals to produce augmenting features via feature-wise linear modulation. The learning process is formulated as a bi-level optimization problem: the inner objective optimizes task performance under fixed prompts, while the outer objective maximizes generalization across the surrogate domains by updating the domain prompt encoder. We further develop a practical gradient approximation scheme that enables efficient bi-level training without second-order derivatives. Extensive experiments on various SGD benchmarks demonstrate that BiSDG consistently outperforms prior methods, setting new state-of-the-art performance in the SDG setting.

Related papers

• BPG: Balancing Plasticity and Generalization for Domain Incremental Learning [48.68747632195046]
  Domain incremental learning enables models to continuously adapt while retaining prior knowledge.<n>We propose BPG, a unified framework that addresses both challenges through two complementary components.<n>BPG consistently outperforms uniform adapter-based approaches and hard domain selection strategies.
  arXiv  Detail & Related papers  (2026-08-11T11:22:27Z)
• StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
  Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data. We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
  arXiv  Detail & Related papers  (2024-06-01T02:41:34Z)
• CDA: Contrastive-adversarial Domain Adaptation [11.354043674822451]
  We propose a two-stage model for domain adaptation called textbfContrastive-adversarial textbfDomain textbfAdaptation textbf(CDA). While the adversarial component facilitates domain-level alignment, two-stage contrastive learning exploits class information to achieve higher intra-class compactness across domains.
  arXiv  Detail & Related papers  (2023-01-10T07:43:21Z)
• Domain Generalisation for Object Detection under Covariate and Concept Shift [10.32461766065764]
  Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features. An approach to domain generalisation for object detection is proposed, the first such approach applicable to any object detection architecture.
  arXiv  Detail & Related papers  (2022-03-10T11:14:18Z)
• Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation [62.68759523116924]
  Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting. We propose a novel feature space Amplitude Spectrum Transformation (AST)
  arXiv  Detail & Related papers  (2022-02-09T05:40:34Z)
• Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer [27.64947077788111]
  Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data adapt to real images. Previous feature-level adversarial learning methods only consider adapting models on the high-level semantic features. We present the first attempt at explicitly using low-level edge information, which has a small inter-domain gap, to guide the transfer of semantic information.
  arXiv  Detail & Related papers  (2021-09-18T11:51:31Z)
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images [93.50240389540252]
  Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field. Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-28T09:29:14Z)
• Domain Adaptive Person Re-Identification via Coupling Optimization [58.567492812339566]
  Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. This paper proposes a coupling optimization method including the Domain-Invariant Mapping (DIM) method and the Global-Local distance Optimization ( GLO) GLO is designed to train the ReID model with unsupervised setting on the target domain.
  arXiv  Detail & Related papers  (2020-11-06T14:01:03Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)
• Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
  Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
  arXiv  Detail & Related papers  (2020-02-12T09:45:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.