mlsanityData to 7 Oct 2026

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

arXiv 2401.05401 ↗First posted 20 Dec 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

43 of 54 references.

References · 43

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Fast R-CNNcited by 2,930
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  11. 2019Invariant Risk Minimizationcited by 1,832
  12. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
31 more
  1. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  2. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  3. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  6. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  7. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  8. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  9. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  10. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  11. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  12. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  13. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  14. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  15. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  16. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  17. 2017Demystifying Neural Style Transfercited by 152
  18. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 136
  19. 2020Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detectorcited by 106
  20. 2019Switchable Whitening for Deep Representation Learningcited by 105
  21. 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
  22. 2019Iterative Normalization: Beyond Standardization towards Efficient Whiteningcited by 92
  23. 2017A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detectioncited by 43
  24. 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
  25. 2019All-In-One Underwater Image Enhancement using Domain-Adversarial Learningcited by 29
  26. 2023Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domainscited by 24
  27. 2019RoIMix: Proposal-Fusion among Multiple Images for Underwater Object Detectioncited by 19
  28. 2021Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learningcited by 12
  29. 2022Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detectioncited by 10
  30. 2020WQT and DG-YOLO: towards domain generalization in underwater object detectioncited by 8
  31. 2022Excavating RoI Attention for Underwater Object Detectioncited by 7

Built on by

Not cited yet.