# Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

arXiv: https://arxiv.org/abs/2007.14449 · HTML: https://mlsanity.com/paper/2007.14449/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2020.

## Built on by (most cited first, 30 of 41)

- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.09600/) (2021)
- [Cross-View Regularization for Domain Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2103.02584/) (2021)
- [All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes](https://mlsanity.com/paper/2312.12176/) (2023)
- [Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.06654/) (2022)
- [Geometric Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16694/) (2021)
- [Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning](https://mlsanity.com/paper/2104.11056/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Dual Path Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2108.06337/) (2021)
- [Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation](https://mlsanity.com/paper/2304.13615/) (2023)
- [Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement](https://mlsanity.com/paper/2310.16979/) (2023)
- [Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation](https://mlsanity.com/paper/2203.01074/) (2022)
- [A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation](https://mlsanity.com/paper/2106.11653/) (2021)
- [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://mlsanity.com/paper/2106.02594/) (2021)
- [UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration](https://mlsanity.com/paper/2206.15083/) (2022)
- [Self-Ensembling GAN for Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2112.07999/) (2021)
- [FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images](https://mlsanity.com/paper/2201.02588/) (2022)
- [Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2309.14241/) (2023)
- [Unsupervised Adaptation of Semantic Segmentation Models without Source Data](https://mlsanity.com/paper/2112.02359/) (2021)
- [Unsupervised Contrastive Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2204.08399/) (2022)
- [Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2208.10716/) (2022)
- [Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning](https://mlsanity.com/paper/2311.04815/) (2023)
- [SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets](https://mlsanity.com/paper/2308.11880/) (2023)
- [Few-shot Object Detection in Remote Sensing: Lifting the Curse of Incompletely Annotated Novel Objects](https://mlsanity.com/paper/2309.10588/) (2023)
- [STAT: Towards Generalizable Temporal Action Localization](https://mlsanity.com/paper/2404.13311/) (2024)
- [QuadFormer: Quadruple Transformer for Unsupervised Domain Adaptation in Power Line Segmentation of Aerial Images](https://mlsanity.com/paper/2211.16988/) (2022)
- [Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2212.04227/) (2022)
- [Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors](https://mlsanity.com/paper/2309.16646/) (2023)
- [Cross-Region Building Counting in Satellite Imagery using Counting Consistency](https://mlsanity.com/paper/2110.13558/) (2021)

## Abstract (arXiv)

Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel approach of exploiting scale-invariance property of the semantic segmentation model for self-supervised domain adaptation. Our algorithm is based on a reasonable assumption that, in general, regardless of the size of the object and stuff (given context) the semantic labeling should be unchanged. We show that this constraint is violated over the images of the target domain, and hence could be used to transfer labels in-between differently scaled patches. Specifically, we show that semantic segmentation model produces output with high entropy when presented with scaled-up patches of target domain, in comparison to when presented original size images. These scale-invariant examples are extracted from the most confident images of the target domain. Dynamic class specific entropy thresholding mechanism is presented to filter out unreliable pseudo-labels. Furthermore, we also incorporate the focal loss to tackle the problem of class imbalance in self-supervised learning. Extensive experiments have been performed, and results indicate that exploiting the scale-invariant labeling, we outperform existing self-supervised based state-of-the-art domain adaptation methods. Specifically, we achieve 1.3% and 3.8% of lead for GTA5 to Cityscapes and SYNTHIA to Cityscapes with VGG16-FCN8 baseline network.