mlsanityData to 7 Oct 2026

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

arXiv 2307.15063 ↗First posted 27 Jul 2023cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high computational costs associated with brute-force adaptation make this paradigm unfeasible for real-world applications. In this paper we propose HAMLET, a Hardware-Aware Modular Least Expensive Training framework for real-time domain adaptation. Our approach includes a hardware-aware back-propagation orchestration agent (HAMT) and a dedicated domain-shift detector that enables active control over when and how the model is adapted (LT). Thanks to these advancements, our approach is capable of performing semantic segmentation while simultaneously adapting at more than 29FPS on a single consumer-grade GPU. Our framework's encouraging accuracy and speed trade-off is demonstrated on OnDA and SHIFT benchmarks through experimental results.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 63 of its 82 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

63 of 82 references.

References · 63

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2018Dual Attention Network for Scene Segmentationcited by 1,001
38 more
  1. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  2. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  3. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  4. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  5. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  6. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  7. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  8. 2022Continual Test-Time Domain Adaptationcited by 520
  9. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  10. 2019Confidence Regularized Self-Trainingcited by 418
  11. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  12. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  13. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  14. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  15. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  16. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  17. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  18. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  19. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  20. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 165
  21. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  22. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  23. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  24. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  25. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  26. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  27. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  28. 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
  29. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  30. 2019Accelerating Deep Learning by Focusing on the Biggest Loserscited by 94
  31. 2018Real-time self-adaptive deep stereocited by 80
  32. 2020Rain rendering for evaluating and improving robustness to bad weathercited by 56
  33. 2017Incremental Adversarial Domain Adaptation for Continually Changing Environmentscited by 52
  34. 2019Adaptive Context Network for Scene Parsingcited by 51
  35. 2015Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transformcited by 46
  36. 2019ACE: Adapting to Changing Environments for Semantic Segmentationcited by 44
  37. 2020Unsupervised Model Adaptation for Continual Semantic Segmentationcited by 42
  38. 2022Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentationcited by 40

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 4; 2026: 5.

14 papers.

Sort:

  1. 2024Federated Online Adaptation for Deep Stereocited by 12
  2. 2025Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentationcited by 7
  3. 2024Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detectioncited by 5
  4. 2024Test Time Training for Industrial Anomaly Segmentationcited by 4
  5. 2024Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bankcited by 3
  6. 2025DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentationcited by 3
  7. 2026Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptationcited by 3
  8. 2023Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisitioncited by 1
  9. 2025Zero-Shot Anomaly Detection with Dual-Branch Prompt Selectioncited by 1
  10. 2025RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereocited by 1
  11. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  12. 2026MUSDA: Multi-source Multi-modality Unsupervised Domain Adaptive 3D Object Detection for Autonomous Drivingcited by 0
2 more
  1. 2026Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentationcited by 0
  2. 2026When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentationcited by 0