Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information

2020-08-27 · Lei Li, Veronika A. Zimmer, Wangbin Ding, Fuping Wu, Liqin Huang, Julia A. Schnabel, Xiahai Zhuang

Deep learning (DL)-based models have demonstrated good performance in medical image segmentation. However, the models trained on a known dataset often fail when performed on an unseen dataset collected from different centers, vendors and disease populations. In this work, we present a random style transfer network to tackle the domain generalization problem for multi-vendor and center cardiac image segmentation. Style transfer is used to generate training data with a wider distribution/ heterogeneity, namely domain augmentation. As the target domain could be unknown, we randomly generate a modality vector for the target modality in the style transfer stage, to simulate the domain shift for unknown domains. The model can be trained in a semi-supervised manner by simultaneously optimizing a supervised segmentation and an unsupervised style translation objective. Besides, the framework incorporates the spatial information and shape prior of the target by introducing two regularization terms. We evaluated the proposed framework on 40 subjects from the M\&Ms challenge2020, and obtained promising performance in the segmentation for data from unknown vendors and centers.

📄 PDF Abstract BibTeX arXiv:2008.12205

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization Image Segmentation Medical Image Segmentation Segmentation Semantic Segmentation Style Transfer Translation

Style Augmentation: Data Augmentation via Style Randomization

2018-09-14 · Philip T. Jackson, Amir Atapour-Abarghouei, Stephen Bonner, Toby Breckon 외

We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. Du…

Classification Data Augmentation Depth Estimation Domain Adaptation+3

Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation

2021-02-02 · Rikiya Yamashita, Jin Long, Snikitha Banda, Jeanne Shen 외

Suboptimal generalization of machine learning models on unseen data is a key challenge which hampers the clinical applicability of such models to medical imaging. Although various methods such as domain adaptation and do…

Data Augmentation Domain Adaptation Domain Generalization Style Transfer

Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning

2023-01-19 · Shuzhen Rao, Jun Huang, Zengming Tang

In cross-domain few-shot learning, the core issue is that the model trained on source domains struggles to generalize to the target domain, especially when the domain shift is large. Motivated by the observation that the…

Cross-Domain Few-Shot cross-domain few-shot learning Diversity Domain Generalization+3

Feature-based Style Randomization for Domain Generalization

2021-06-06 · Yue Wang, Lei Qi, Yinghuan Shi, Yang Gao

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. I…

Data Augmentation Diversity Domain Generalization

Evaluation of Randomization through Style Transfer for Enhanced Domain Generalization

2026-04-07 · Dustin Eisenhardt, Timothy Schaumlöffel, Alperen Kantarci, Gemma Roig arxiv

Deep learning models for computer vision often suffer from poor generalization when deployed in real-world settings, especially when trained on synthetic data due to the well-known Sim2Real gap. Despite the growing popul…

Domain Generalization Scene Understanding Data Augmentation Style Transfer