Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection

• URL: http://arxiv.org/abs/2504.20498v1
• Date: Tue, 29 Apr 2025 07:38:37 GMT
• Title: Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection
• Authors: Jianhong Han, Yupei Wang, Liang Chen,
• Abstract summary: Single-source Domain Generalization (SDG) in object detection aims to develop a detector using only data from a source domain.<n>We propose an object-aware contrastive learning module to guide the detector in extracting domain-invariant features.<n>Experiments demonstrate the superior performance and generalization capability of SA-DETR across five different weather scenarios.
• Score: 7.768332621617199
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Single-source Domain Generalization (SDG) in object detection aims to develop a detector using only data from a source domain that can exhibit strong generalization capability when applied to unseen target domains. Existing methods are built upon CNN-based detectors and primarily improve robustness by employing carefully designed data augmentation strategies integrated with feature alignment techniques. However, data augmentation methods have inherent drawbacks; they are only effective when the augmented sample distribution approximates or covers the unseen scenarios, thus failing to enhance generalization across all unseen domains. Furthermore, while the recent Detection Transformer (DETR) has demonstrated superior generalization capability in domain adaptation tasks due to its efficient global information extraction, its potential in SDG tasks remains unexplored. To this end, we introduce a strong DETR-based detector named the Style-Adaptive Detection Transformer (SA-DETR) for SDG in object detection. Specifically, we present a domain style adapter that projects the style representation of the unseen target domain into the training domain, enabling dynamic style adaptation. Then, we propose an object-aware contrastive learning module to guide the detector in extracting domain-invariant features through contrastive learning. By using object-aware gating masks to constrain feature aggregation in both spatial and semantic dimensions, this module achieves cross-domain contrast of instance-level features, thereby enhancing generalization. Extensive experiments demonstrate the superior performance and generalization capability of SA-DETR across five different weather scenarios. Code is released at https://github.com/h751410234/SA-DETR.

Related papers

• DG-DETR: Toward Domain Generalized Detection Transformer [8.762314897895175]
  We introduce a Domain Generalized DEtection TRansformer (DG-DETR) to enhance the robustness of Transformer-based detectors.<n>Specifically, we propose a novel domain-agnostic query selection strategy that removes domain-induced biases from object queries.<n> Experimental results validate the effectiveness of DG-DETR.
  arXiv  Detail & Related papers  (2025-04-28T08:33:10Z)
• RT-DATR:Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Learning [4.823481349001852]
  We propose RT-DATR, a real-time domain adaptive detection transformer. Our method outperforms current state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-04-12T12:36:01Z)
• Object Style Diffusion for Generalized Object Detection in Urban Scene [69.04189353993907]
  We introduce a novel single-domain object detection generalization method, named GoDiff.<n>By integrating pseudo-target domain data with source domain data, we diversify the training dataset.<n> Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods.
  arXiv  Detail & Related papers  (2024-12-18T13:03:00Z)
• DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment [7.768332621617199]
  We introduce a strong DETR-based detector named Domain Adaptive detection TRansformer ( DATR) for unsupervised domain adaptation of object detection. Our proposed DATR incorporates a mean-teacher based self-training framework, utilizing pseudo-labels generated by the teacher model to further mitigate domain bias. Experiments demonstrate superior performance and generalization capabilities of our proposed DATR in multiple domain adaptation scenarios.
  arXiv  Detail & Related papers  (2024-05-20T03:48:45Z)
• Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector [72.05791402494727]
  This paper studies the challenging cross-domain few-shot object detection (CD-FSOD) It aims to develop an accurate object detector for novel domains with minimal labeled examples.
  arXiv  Detail & Related papers  (2024-02-05T15:25:32Z)
• CLIP the Gap: A Single Domain Generalization Approach for Object Detection [60.20931827772482]
  Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
  arXiv  Detail & Related papers  (2023-01-13T12:01:18Z)
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [79.89082006155135]
  Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. UDA methods try to align the source and target representations to improve the generalization on the target domain. The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
  arXiv  Detail & Related papers  (2022-03-29T17:50:43Z)
• 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)
• Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement [79.2994130944482]
  We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
  arXiv  Detail & Related papers  (2022-01-06T05:43:01Z)
• DA-DETR: Domain Adaptive Detection Transformer with Information Fusion [53.25930448542148]
  DA-DETR is a domain adaptive object detection transformer that introduces information fusion for effective transfer from a labeled source domain to an unlabeled target domain. We introduce a novel CNN-Transformer Blender (CTBlender) that fuses the CNN features and Transformer features ingeniously for effective feature alignment and knowledge transfer across domains. CTBlender employs the Transformer features to modulate the CNN features across multiple scales where the high-level semantic information and the low-level spatial information are fused for accurate object identification and localization.
  arXiv  Detail & Related papers  (2021-03-31T13:55:56Z)

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.