# DAWA: Dynamic Ambiguity-Wise Adaptation for Real-Time Domain Adaptive Semantic Segmentation

arXiv: https://arxiv.org/abs/2409.01072 · HTML: https://mlsanity.com/paper/2409.01072/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## Builds on (most cited first, 24 of 24)

- [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)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining](https://mlsanity.com/paper/2404.09476/) (2024)
- [Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions](https://mlsanity.com/paper/2207.06825/) (2022)
- [Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation](https://mlsanity.com/paper/2312.12480/) (2023)
- [Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction](https://mlsanity.com/paper/2303.09792/) (2023)
- [Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions](https://mlsanity.com/paper/2207.10667/) (2022)
- [Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion](https://mlsanity.com/paper/2206.04879/) (2022)
- [VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions](https://mlsanity.com/paper/2211.12256/) (2022)
- [When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather](https://mlsanity.com/paper/2403.13762/) (2024)

## Abstract (arXiv)

Test-time domain adaption (TTDA) for semantic segmentation aims to adapt a segmentation model trained on a source domain to a target domain for inference on-the-fly, where both efficiency and effectiveness are critical. However, existing TTDA methods either rely on costly frame-wise optimization or assume unrealistic domain shifts, resulting in poor adaptation efficiency and continuous semantic ambiguities. To address these challenges, we propose a real-time framework for TTDA semantic segmentation, called Dynamic Ambiguity-Wise Adaptation (DAWA), which adaptively detects domain shifts and dynamically adjusts the learning strategies to mitigate continuous ambiguities in the test time. Specifically, we introduce the Dynamic Ambiguous Patch Mask (DAP Mask) strategy, which dynamically identifies and masks highly disturbed regions to prevent error accumulation in ambiguous classes. Furthermore, we present the Dynamic Ambiguous Class Mix (DAC Mix) strategy that leverages vision-language models to group semantically similar classes and augment the target domain with a meta-ambiguous class buffer. Extensive experiments on widely used TTDA benchmarks demonstrate that DAWA consistently outperforms state-of-the-art methods, while maintaining real-time inference speeds of approximately 40 FPS.