# Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization

arXiv: https://arxiv.org/abs/2003.12296 · HTML: https://mlsanity.com/paper/2003.12296/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2020.

## Built on by (most cited first, 20 of 20)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention](https://mlsanity.com/paper/2303.13014/) (2023)
- [MVDG: A Unified Multi-view Framework for Domain Generalization](https://mlsanity.com/paper/2112.12329/) (2021)
- [DomainAdaptor: A Novel Approach to Test-time Adaptation](https://mlsanity.com/paper/2308.10297/) (2023)
- [Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights](https://mlsanity.com/paper/2407.07586/) (2024)
- [Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization](https://mlsanity.com/paper/2407.15085/) (2024)
- [A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2201.09846/) (2022)
- [Shadow-Aware Dynamic Convolution for Shadow Removal](https://mlsanity.com/paper/2205.04908/) (2022)
- [Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2110.04820/) (2021)
- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2208.05853/) (2022)
- [Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning](https://mlsanity.com/paper/2203.10395/) (2022)
- [Label Distribution Learning for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2204.05903/) (2022)
- [Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training](https://mlsanity.com/paper/2507.07778/) (2025)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework](https://mlsanity.com/paper/2111.15077/) (2021)
- [Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation](https://mlsanity.com/paper/2309.14282/) (2023)
- [LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation](https://mlsanity.com/paper/2403.11122/) (2024)
- [Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation](https://mlsanity.com/paper/2507.11955/) (2025)

## Abstract (arXiv)

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years. However, its performance usually drops dramatically due to the data-distribution discrepancy between seen and unseen domains when we directly deploy the trained model to segment the images of unseen (or new coming) domains. To this end, we propose a novel domain generalization framework for the generalizable semantic segmentation task, which enhances the generalization ability of the model from two different views, including the training paradigm and the test strategy. Concretely, we exploit the model-agnostic learning to simulate the domain shift problem, which deals with the domain generalization from the training scheme perspective. Besides, considering the data-distribution discrepancy between seen source and unseen target domains, we develop the target-specific normalization scheme to enhance the generalization ability. Furthermore, when images come one by one in the test stage, we design the image-based memory bank (Image Bank in short) with style-based selection policy to select similar images to obtain more accurate statistics of normalization. Extensive experiments highlight that the proposed method produces state-of-the-art performance for the domain generalization of semantic segmentation on multiple benchmark segmentation datasets, i.e., Cityscapes, Mapillary.