# Domain Adaptive Semantic Segmentation Using Weak Labels

arXiv: https://arxiv.org/abs/2007.15176 · HTML: https://mlsanity.com/paper/2007.15176/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 30 of 56)

- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [WildNet: Learning Domain Generalized Semantic Segmentation from the Wild](https://mlsanity.com/paper/2204.01446/) (2022)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.00085/) (2021)
- [Learning Cross-modal Contrastive Features for Video Domain Adaptation](https://mlsanity.com/paper/2108.11974/) (2021)
- [DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.09600/) (2021)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.06654/) (2022)
- [LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.05570/) (2021)
- [Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.07830/) (2021)
- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning](https://mlsanity.com/paper/2104.11056/) (2021)
- [Multi-Granularity Alignment Domain Adaptation for Object Detection](https://mlsanity.com/paper/2203.16897/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition](https://mlsanity.com/paper/2403.14082/) (2024)
- [Hyperbolic Active Learning for Semantic Segmentation under Domain Shift](https://mlsanity.com/paper/2306.11180/) (2023)
- [Cross-Modal Knowledge Transfer Without Task-Relevant Source Data](https://mlsanity.com/paper/2209.04027/) (2022)
- [Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization](https://mlsanity.com/paper/2110.05170/) (2021)
- [PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2406.06679/) (2024)
- [ESA: Annotation-Efficient Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2408.13491/) (2024)
- [Learning Semantic Segmentation from Multiple Datasets with Label Shifts](https://mlsanity.com/paper/2202.14030/) (2022)
- [Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation](https://mlsanity.com/paper/2112.00295/) (2021)
- [PressureVision++: Estimating Fingertip Pressure from Diverse RGB Images](https://mlsanity.com/paper/2301.02310/) (2023)
- [A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation](https://mlsanity.com/paper/2106.11653/) (2021)
- [Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2204.05546/) (2022)
- [Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation](https://mlsanity.com/paper/2212.07911/) (2022)
- [Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries](https://mlsanity.com/paper/2110.02833/) (2021)

## Abstract (arXiv)

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In this work, we propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain. The weak labels may be obtained based on a model prediction for unsupervised domain adaptation (UDA), or from a human annotator in a new weakly-supervised domain adaptation (WDA) paradigm for semantic segmentation. Using weak labels is both practical and useful, since (i) collecting image-level target annotations is comparably cheap in WDA and incurs no cost in UDA, and (ii) it opens the opportunity for category-wise domain alignment. Our framework uses weak labels to enable the interplay between feature alignment and pseudo-labeling, improving both in the process of domain adaptation. Specifically, we develop a weak-label classification module to enforce the network to attend to certain categories, and then use such training signals to guide the proposed category-wise alignment method. In experiments, we show considerable improvements with respect to the existing state-of-the-arts in UDA and present a new benchmark in the WDA setting. Project page is at http://www.nec-labs.com/~mas/WeakSegDA.