mlsanityData to 7 Oct 2026

FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions

arXiv 2407.13437 ↗First posted 18 Jul 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Robust semantic segmentation under adverse conditions is crucial in real-world applications. To address this challenging task in practical scenarios where labeled normal condition images are not accessible in training, we propose FREST, a novel feature restoration framework for source-free domain adaptation (SFDA) of semantic segmentation to adverse conditions. FREST alternates two steps: (1) learning the condition embedding space that only separates the condition information from the features and (2) restoring features of adverse condition images on the learned condition embedding space. By alternating these two steps, FREST gradually restores features where the effect of adverse conditions is reduced. FREST achieved a state of the art on two public benchmarks (i.e., ACDC and RobotCar) for SFDA to adverse conditions. Moreover, it shows superior generalization ability on unseen datasets.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 18 Jul 2024.

Builds on

43 of 56 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  8. 2020Supervised Contrastive Learningcited by 2,803
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  11. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  12. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
31 more
  1. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  2. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  3. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  4. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  5. 2019Confidence Regularized Self-Trainingcited by 418
  6. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  7. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  8. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  9. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  10. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  11. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  12. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  13. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  14. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  15. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  16. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  17. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  18. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  19. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  20. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  21. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  22. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  23. 2018Fast Human Pose Estimationcited by 68
  24. 2019Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understandingcited by 40
  25. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  26. 2022Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditionscited by 31
  27. 2019A Cross-Season Correspondence Dataset for Robust Semantic Segmentationcited by 28
  28. 2020URIE: Universal Image Enhancement for Visual Recognition in the Wildcited by 27
  29. 2023Human Pose Estimation in Extremely Low-Light Conditionscited by 27
  30. 2022SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentationcited by 17
  31. 2023Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 5.

7 papers.

  1. 2024Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentationcited by 5
  2. 2025Transforming Future Data Center Operations and Management via Physical AIcited by 3
  3. 2026The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Modelscited by 2
  4. 2026Restoration Adaptation for Semantic Segmentation on Low Quality Imagescited by 1
  5. 2026Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditionscited by 1
  6. 2026Robust Promptable Video Object Segmentationcited by 0
  7. 2026Ultra: Unsupervised Cross-Task Optimization for Reliable Restoration Segmentation Collaboration under Adverse Weathercited by 0