mlsanityData to 7 Oct 2026

BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

arXiv 2108.03267 ↗First posted 6 Aug 2021cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation aims to predict pixel-level labels. It has become a popular task in various computer vision applications. While fully supervised segmentation methods have achieved high accuracy on large-scale vision datasets, they are unable to generalize on a new test environment or a new domain well. In this work, we first introduce a new Un-aligned Domain Score to measure the efficiency of a learned model on a new target domain in unsupervised manner. Then, we present the new Bijective Maximum Likelihood(BiMaL) loss that is a generalized form of the Adversarial Entropy Minimization without any assumption about pixel independence. We have evaluated the proposed BiMaL on two domains. The proposed BiMaL approach consistently outperforms the SOTA methods on empirical experiments on "SYNTHIA to Cityscapes", "GTA5 to Cityscapes", and "SYNTHIA to Vistas".

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 40 of its 60 references that are in the map. First posted on arXiv 6 Aug 2021.

Builds on

40 of 60 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  11. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  12. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
28 more
  1. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  2. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  3. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  4. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  5. 2015Unifying distillation and privileged informationcited by 218
  6. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  7. 2017Image to Image Translation for Domain Adaptationcited by 171
  8. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  9. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  10. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  11. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  12. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  13. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  14. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  15. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  16. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
  17. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  18. 2018SPIGAN: Privileged Adversarial Learning from Simulationcited by 47
  19. 2020Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognitioncited by 36
  20. 2018Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptationcited by 29
  21. 2017Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentationcited by 16
  22. 2018Automatic Face Aging in Videos via Deep Reinforcement Learningcited by 16
  23. 2017Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognitioncited by 15
  24. 2019ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networkscited by 12
  25. 2016Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machinescited by 10
  26. 2019Fast Flow Reconstruction via Robust Invertible nxn Convolutioncited by 6
  27. 2016Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modelingcited by 5
  28. 2017Adaptive SVM+: Learning with Privileged Information for Domain Adaptationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 12; 2024: 1; 2025: 5; 2026: 3.

31 papers.

Sort:

By area:

  1. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  2. 2022DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognitioncited by 31
  3. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  4. 2023Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understandingcited by 29
  5. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
  6. 2021Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understandingcited by 26
  7. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  8. 2022DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentationcited by 22
  9. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  10. 2021Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularizationcited by 16
  11. 2023Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environmentscited by 16
  12. 2023Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspectivecited by 14
19 more
  1. 2023FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understandingcited by 13
  2. 2022OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptationcited by 12
  3. 2022Self-supervised Domain Adaptation in Crowd Countingcited by 11
  4. 2022CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Carscited by 11
  5. 2023Informative Data Mining for One-Shot Cross-Domain Semantic Segmentationcited by 7
  6. 2025Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understandingcited by 7
  7. 2022Unsupervised Contrastive Domain Adaptation for Semantic Segmentationcited by 6
  8. 2024EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understandingcited by 6
  9. 2025varphi-Adapt: A Physics-Informed Adaptation Learning Approach to 2D Quantum Material Discoverycited by 3
  10. 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learningcited by 3
  11. 2023CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptationcited by 2
  12. 2023CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentationcited by 2
  13. 2025CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identificationcited by 2
  14. 2026φ-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Modelscited by 2
  15. 2023UTOPIA: Unconstrained Tracking Objects without Preliminary Examination via Cross-Domain Adaptationcited by 1
  16. 2023Dual-level Interaction for Domain Adaptive Semantic Segmentationcited by 1
  17. 2025BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Modelscited by 1
  18. 2026OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materialscited by 1
  19. 2026α-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modelingcited by 0