mlsanityData to 14 Oct 2026

Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentation

arXiv 2505.07050 ↗First posted 11 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) aims to align source and target domain distributions to close the domain gap, but still struggles with obtaining the target data. Fortunately, Domain Generalization (DG) excels without the need for any target data. Recent works expose that depth maps contribute to improved generalized performance in the UDA tasks, but they ignore the noise and holes in depth maps due to device and environmental factors, failing to sufficiently and effectively learn domain-invariant representation. Although high-sensitivity region suppression has shown promising results in learning domain-invariant features, existing methods cannot be directly applicable to depth maps due to their unique characteristics. Hence, we propose a novel framework, namely Depth-Sensitive Soft Suppression with RGB-D inter-modal stylization flow (DSSS), focusing on learning domain-invariant features from depth maps for the DG semantic segmentation. Specifically, we propose the RGB-D inter-modal stylization flow to generate stylized depth maps for sensitivity detection, cleverly utilizing RGB information as the stylization source. Then, a class-wise soft spatial sensitivity suppression is designed to identify and emphasize non-sensitive depth features that contain more domain-invariant information. Furthermore, an RGB-D soft alignment loss is proposed to ensure that the stylized depth maps only align part of the RGB features while still retaining the unique depth information. To our best knowledge, our DSSS framework is the first work to integrate RGB and Depth information in the multi-class DG semantic segmentation task. Extensive experiments over multiple backbone networks show that our framework achieves remarkable performance improvement.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 60 references that are in the map. First posted on arXiv 11 May 2025.

Builds on

35 of 60 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  6. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  7. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  8. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  9. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  10. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  11. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 364
  12. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
23 more
  1. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 246
  2. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 231
  3. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  4. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  5. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  6. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  7. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  8. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
  9. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  10. 2020Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentationcited by 122
  11. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  12. 2019ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentationcited by 107
  13. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  14. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 76
  15. 2022SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detectioncited by 59
  16. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 57
  17. 2018SPIGAN: Privileged Adversarial Learning from Simulationcited by 47
  18. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 39
  19. 2020Affinity Space Adaptation for Semantic Segmentation Across Domainscited by 31
  20. 2022SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpointscited by 22
  21. 2024MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentationcited by 13
  22. 2023InfraParis: A multi-modal and multi-task autonomous driving datasetcited by 12
  23. 2022AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptationcited by 1

Built on by

Not cited yet.