Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection

• URL: http://arxiv.org/abs/2401.05401v1
• Date: Wed, 20 Dec 2023 05:45:56 GMT
• Title: Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection
• Abstract summary: This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP) Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC 2020.
• Score: 18.39732229138302
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. When the test set is collected in a different marine area from the training set, the issue of domain shift emerges, significantly compromising the model's ability to generalize. The Domain Adversarial Learning (DAL) training strategy has been previously utilized to tackle such challenges. However, DAL heavily depends on manually one-hot domain labels, which implies no difference among the samples in the same domain. Such an assumption results in the instability of DAL. This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP). The domain label for each image is regarded as its similarity to the specified domains. Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. Furthermore, we validated the effectiveness of our method in the Cityscapes dataset.

Related papers

• Why Domain Matters: Domain-Aware Benchmarking of Underwater Object Detection and Annotation Quality [9.468095570700642]
  We introduce a framework that characterizes underwater images by appearance, scene composition, and acquisition geometry to assign domain labels.<n>We perform the first systematic study of how domain factors influence both human annotation quality in underwater object detection datasets and deep learning-based detector performance.<n>We highlight how this can be used to guide data collection and annotation, design more informative benchmarks, and assess detector robustness across diverse underwater environments.
  arXiv  Detail & Related papers  (2026-07-12T05:11:59Z)
• Why Domain Matters: A Preliminary Study of Domain Effects in Underwater Object Detection [9.468095570700642]
  We propose a labeling framework that defines underwater domains using measurable image, scene, and acquisition characteristics.<n>Unlike prior benchmarks, it captures physically meaningful factors, enabling semantically consistent image grouping and supporting domain-specific evaluation of detection performance including failure analysis.
  arXiv  Detail & Related papers  (2026-04-28T23:28:14Z)
• ConstStyle: Robust Domain Generalization with Unified Style Transformation [16.853951836297203]
  Domain Generalization (DG) aims to address this by focusing on domain-invariant features or augmenting data for greater diversity.<n>We propose ConstStyle, a novel approach that leverages a unified domain to capture domain-invariant features and bridge the domain gap with theoretical analysis.
  arXiv  Detail & Related papers  (2025-09-07T08:40:19Z)
• Cyclically Disentangled Feature Translation for Face Anti-spoofing [61.70377630461084]
  We propose a novel domain adaptation method called cyclically disentangled feature translation network (CDFTN) CDFTN generates pseudo-labeled samples that possess: 1) source domain-invariant liveness features and 2) target domain-specific content features, which are disentangled through domain adversarial training. A robust classifier is trained based on the synthetic pseudo-labeled images under the supervision of source domain labels.
  arXiv  Detail & Related papers  (2022-12-07T14:12:34Z)
• Unsupervised Domain Adaptation for Extra Features in the Target Domain Using Optimal Transport [3.6042575355093907]
  Most domain adaptation methods assume that the source and target domains have the same dimensionality. In this paper, it is assumed that common features exist in both domains and that extra (new additional) features are observed in the target domain. To leverage the homogeneity of the common features, the adaptation between these source and target domains is formulated as an optimal transport problem.
  arXiv  Detail & Related papers  (2022-09-10T04:35:58Z)
• Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification [50.658613573816254]
  We propose a novel Multi-scale Multi-target Domain Adversarial Network (M2DAN) for angle closure classification. Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains.
  arXiv  Detail & Related papers  (2022-08-25T15:27:55Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• Achieving Domain Generalization in Underwater Object Detection by Image Stylization and Domain Mixup [8.983901488753967]
  Existing underwater object detection methods degrade seriously when facing domain shift problem caused by complicated underwater environments. We propose a domain generalization method from the aspect of data augmentation. Comprehensive experiments on S-UODAC 2020 datasets demonstrate that the proposed method is able to learn domain-invariant representations.
  arXiv  Detail & Related papers  (2021-04-06T01:45:07Z)
• Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
  Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
  arXiv  Detail & Related papers  (2021-03-25T15:28:41Z)
• Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation [67.83872616307008]
  Unversarial Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. In this paper, we propose a novel Adrial Dual Distincts Network (AD$2$CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment.
  arXiv  Detail & Related papers  (2020-08-27T01:29:10Z)
• DACS: Domain Adaptation via Cross-domain Mixed Sampling [4.205692673448206]
  Unsupervised domain adaptation attempts to train on labelled data from one domain, and simultaneously learn from unlabelled data in the domain of interest. We propose DACS: Domain Adaptation via Cross-domain mixed Sampling, which mixes images from the two domains along with the corresponding labels and pseudo-labels. We demonstrate the effectiveness of our solution by achieving state-of-the-art results for GTA5 to Cityscapes.
  arXiv  Detail & Related papers  (2020-07-17T00:43:11Z)
• 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)
• Adapting Object Detectors with Conditional Domain Normalization [38.13526570506076]
  Conditional Domain Normalization (CDN) is designed to encode different domain inputs into a shared latent space. We incorporate CDN into various convolution stages of an object detector to adaptively address the domain shifts of different level's representation. Tests show that CDN outperforms existing methods remarkably on both real-to-real and synthetic-to-real adaptation benchmarks.
  arXiv  Detail & Related papers  (2020-03-16T08:27:29Z)

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.