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

arXiv: https://arxiv.org/abs/2108.03267 · HTML: https://mlsanity.com/paper/2108.03267/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 60 references that are in the map.
- First posted on arXiv 6 Aug 2021.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/1910.13049/) (2019)
- [Domain Adaptation for Structured Output via Discriminative Patch Representations](https://mlsanity.com/paper/1901.05427/) (2019)
- [Domain Adaptation for Semantic Segmentation with Maximum Squares Loss](https://mlsanity.com/paper/1909.13589/) (2019)
- [No More Discrimination: Cross City Adaptation of Road Scene Segmenters](https://mlsanity.com/paper/1704.08509/) (2017)
- [DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation](https://mlsanity.com/paper/1804.05827/) (2018)
- [Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding](https://mlsanity.com/paper/1808.01265/) (2018)
- [DADA: Depth-aware Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1904.01886/) (2019)
- [Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks](https://mlsanity.com/paper/1511.06390/) (2015)
- [ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes](https://mlsanity.com/paper/1711.11556/) (2017)
- [Learning to Self-Train for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1906.00562/) (2019)
- [SPIGAN: Privileged Adversarial Learning from Simulation](https://mlsanity.com/paper/1810.03756/) (2018)

## Built on by (most cited first, 30 of 31)

- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition](https://mlsanity.com/paper/2203.10233/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding](https://mlsanity.com/paper/2311.15206/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding](https://mlsanity.com/paper/2304.02135/) (2023)
- [Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding](https://mlsanity.com/paper/2112.00484/) (2021)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization](https://mlsanity.com/paper/2110.05170/) (2021)
- [Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments](https://mlsanity.com/paper/2305.15700/) (2023)
- [Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective](https://mlsanity.com/paper/2305.15699/) (2023)
- [FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding](https://mlsanity.com/paper/2311.15965/) (2023)
- [OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation](https://mlsanity.com/paper/2205.10738/) (2022)
- [Self-supervised Domain Adaptation in Crowd Counting](https://mlsanity.com/paper/2206.03431/) (2022)
- [CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars](https://mlsanity.com/paper/2212.00621/) (2022)
- [Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2309.14241/) (2023)
- [Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding](https://mlsanity.com/paper/2502.09906/) (2025)
- [Unsupervised Contrastive Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2204.08399/) (2022)
- [EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding](https://mlsanity.com/paper/2406.01429/) (2024)
- [CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation](https://mlsanity.com/paper/2304.07199/) (2023)
- [varphi-Adapt: A Physics-Informed Adaptation Learning Approach to 2D Quantum Material Discovery](https://mlsanity.com/paper/2507.05184/) (2025)
- [MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning](https://mlsanity.com/paper/2508.10133/) (2025)
- [CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentation](https://mlsanity.com/paper/2304.07372/) (2023)
- [CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification](https://mlsanity.com/paper/2508.17261/) (2025)
- [φ-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models](https://mlsanity.com/paper/2602.22601/) (2026)
- [UTOPIA: Unconstrained Tracking Objects without Preliminary Examination via Cross-Domain Adaptation](https://mlsanity.com/paper/2306.09613/) (2023)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models](https://mlsanity.com/paper/2505.24649/) (2025)
- [OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials](https://mlsanity.com/paper/2603.17043/) (2026)

## 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".