mlsanityData to 14 Oct 2026

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

arXiv 2203.06811 ↗First posted 14 Mar 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretrained domain-specific models. To do so, we design a multi-target domain transfer network (MTDT-Net) that aligns visual attributes across domains by transferring the domain distinctive features through a new target adaptive denormalization (TAD) module. Moreover, we propose a bi-directional adaptive region selection (BARS) that reduces the attribute ambiguity among the class labels by adaptively selecting the regions with consistent feature statistics. We show that our single MTDT-Net can synthesize visually pleasing domain transferred images with complex driving datasets, and BARS effectively filters out the unnecessary region of training images for each target domain. With the collaboration of MTDT-Net and BARS, our ADAS achieves state-of-the-art performance for multi-target domain adaptation (MTDA). To the best of our knowledge, our method is the first MTDA method that directly adapts to multiple domains in semantic segmentation.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 55 of its 63 references that are in the map. First posted on arXiv 14 Mar 2022.

Builds on

55 of 63 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
38 more
  1. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  3. 2018Group Normalizationcited by 1,524
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  7. 2016Least Squares Generative Adversarial Networkscited by 1,001
  8. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  9. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  10. 2017Wasserstein GANcited by 639
  11. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  12. 2017Unsupervised Image-to-Image Translation Networkscited by 603
  13. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  14. 2016A Learned Representation For Artistic Stylecited by 341
  15. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 308
  16. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  17. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  18. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  19. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  20. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  21. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 243
  22. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  23. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  24. 2016Coupled Generative Adversarial Networkscited by 216
  25. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  26. 2017Image to Image Translation for Domain Adaptationcited by 171
  27. 2018IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environmentscited by 163
  28. 2016Unsupervised Cross-Domain Image Generationcited by 125
  29. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  30. 2019Domain Agnostic Learning with Disentangled Representationscited by 108
  31. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  32. 2018Batch-Instance Normalization for Adaptively Style-Invariant Neural Networkscited by 78
  33. 2019Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentationcited by 74
  34. 2021Enhancing Photorealism Enhancementcited by 74
  35. 2018Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approachcited by 63
  36. 2020Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillationcited by 47
  37. 2021Multi-Target Domain Adaptation with Collaborative Consistency Learningcited by 43
  38. 2021DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptationcited by 37

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 4.

10 papers.

  1. 2022Deliberated Domain Bridging for Domain Adaptive Semantic Segmentationcited by 31
  2. 2023Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentationcited by 27
  3. 2024Training-Free Model Merging for Multi-target Domain Adaptationcited by 15
  4. 2023Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptationcited by 9
  5. 2022VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditionscited by 7
  6. 2024Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retentioncited by 4
  7. 2022Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentationcited by 3
  8. 2023Explainable Semantic Medical Image Segmentation with Stylecited by 0
  9. 2024OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentationcited by 0
  10. 2024Multi-Target Unsupervised Domain Adaptation for Semantic Segmentation without External Datacited by 0