# Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings

arXiv: https://arxiv.org/abs/2011.12616 · HTML: https://mlsanity.com/paper/2011.12616/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 25 of 25)

- [Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations](https://mlsanity.com/paper/2103.06342/) (2021)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [Cross-domain Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.05528/) (2021)
- [Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2303.14360/) (2023)
- [Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2205.00858/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Prototype Guided Federated Learning of Visual Feature Representations](https://mlsanity.com/paper/2105.08982/) (2021)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2104.02633/) (2021)
- [Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning](https://mlsanity.com/paper/2306.01598/) (2023)
- [Federated Semi-Supervised Learning with Prototypical Networks](https://mlsanity.com/paper/2205.13921/) (2022)
- [Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels](https://mlsanity.com/paper/2208.02804/) (2022)
- [Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2201.06974/) (2022)
- [Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations](https://mlsanity.com/paper/2108.03021/) (2021)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixing](https://mlsanity.com/paper/2211.02307/) (2022)
- [Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation](https://mlsanity.com/paper/2304.07560/) (2023)
- [Subtype-Aware Dynamic Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.07754/) (2022)
- [Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs](https://mlsanity.com/paper/2407.10534/) (2024)
- [Synthetic-to-real Composite Semantic Segmentation in Additive Manufacturing](https://mlsanity.com/paper/2210.07466/) (2022)
- [Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation](https://mlsanity.com/paper/2310.07149/) (2023)
- [Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2412.16859/) (2024)
- [Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization](https://mlsanity.com/paper/2110.07376/) (2021)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)

## Abstract (arXiv)

Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from label-abundant domains to unlabeled ones. In this paper we propose an effective Unsupervised Domain Adaptation (UDA) strategy, based on a feature clustering method that captures the different semantic modes of the feature distribution and groups features of the same class into tight and well-separated clusters. Furthermore, we introduce two novel learning objectives to enhance the discriminative clustering performance: an orthogonality loss forces spaced out individual representations to be orthogonal, while a sparsity loss reduces class-wise the number of active feature channels. The joint effect of these modules is to regularize the structure of the feature space. Extensive evaluations in the synthetic-to-real scenario show that we achieve state-of-the-art performance.