mlsanityData to 14 Oct 2026

Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime

arXiv 1810.02575 ↗First posted 5 Oct 2018cs.CVcited by 122

Not on the map. Why?

Abstract (arXiv)

This work addresses the problem of semantic image segmentation of nighttime scenes. Although considerable progress has been made in semantic image segmentation, it is mainly related to daytime scenarios. This paper proposes a novel method to progressive adapt the semantic models trained on daytime scenes, along with large-scale annotations therein, to nighttime scenes via the bridge of twilight time -- the time between dawn and sunrise, or between sunset and dusk. The goal of the method is to alleviate the cost of human annotation for nighttime images by transferring knowledge from standard daytime conditions. In addition to the method, a new dataset of road scenes is compiled; it consists of 35,000 images ranging from daytime to twilight time and to nighttime. Also, a subset of the nighttime images are densely annotated for method evaluation. Our experiments show that our method is effective for model adaptation from daytime scenes to nighttime scenes, without using extra human annotation.

Key facts. Cited by 122 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 30; 2023: 32; 2024: 18; 2025: 19; 2026: 5.

122 papers.

Sort:

By area:

  1. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 434
  2. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  3. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  4. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  5. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  6. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  7. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  8. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  9. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  10. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  11. 2021DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentationcited by 80
  12. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
38 more
  1. 2022Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptationcited by 67
  2. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  3. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 66
  4. 2022PODA: Prompt-driven Zero-shot Domain Adaptationcited by 60
  5. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  6. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  7. 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
  8. 2023Instance Segmentation in the Darkcited by 46
  9. 2023Text-image Alignment for Diffusion-based Perceptioncited by 42
  10. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  11. 2022Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentationcited by 40
  12. 2022Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditionscited by 31
  13. 20232PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detectioncited by 31
  14. 2023CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentationcited by 30
  15. 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
  16. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  17. 2021Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 25
  18. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  19. 2021Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Visioncited by 22
  20. 2021ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perceptioncited by 21
  21. 2022CAFA: Class-Aware Feature Alignment for Test-Time Adaptationcited by 21
  22. 2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
  23. 2022Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillationcited by 19
  24. 2022When Does Group Invariant Learning Survive Spurious Correlations?cited by 18
  25. 2022Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filterscited by 17
  26. 2023Boosting Object Detection with Zero-Shot Day-Night Domain Adaptationcited by 17
  27. 2023Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinementcited by 16
  28. 2025FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentationcited by 16
  29. 2021Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrologycited by 15
  30. 2023Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalizationcited by 14
  31. 2024CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuningcited by 13
  32. 2024QT-DoG: Quantization-aware Training for Domain Generalizationcited by 13
  33. 2022Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalizationcited by 12
  34. 2022Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Datacited by 12
  35. 2023Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentationcited by 12
  36. 2023Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglementcited by 12
  37. 2023InfraParis: A multi-modal and multi-task autonomous driving datasetcited by 12
  38. 2022IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenescited by 11

50 most cited of 122 All 122 (JSON)