paper-with-me

홈 › Papers

Mind The Gap: Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation

2022-05-24 · Zixian Su, Kai Yao, Xi Yang, Qiufeng Wang, Yuyao Yan, Jie Sun, Kaizhu Huang

Unsupervised cross-modality medical image adaptation aims to alleviate the severe domain gap between different imaging modalities without using the target domain label. A key in this campaign relies upon aligning the distributions of source and target domain. One common attempt is to enforce the global alignment between two domains, which, however, ignores the fatal local-imbalance domain gap problem, i.e., some local features with larger domain gap are harder to transfer. Recently, some methods conduct alignment focusing on local regions to improve the efficiency of model learning. While this operation may cause a deficiency of critical information from contexts. To tackle this limitation, we propose a novel strategy to alleviate the domain gap imbalance considering the characteristics of medical images, namely Global-Local Union Alignment. Specifically, a feature-disentanglement style-transfer module first synthesizes the target-like source-content images to reduce the global domain gap. Then, a local feature mask is integrated to reduce the 'inter-gap' for local features by prioritizing those discriminative features with larger domain gap. This combination of global and local alignment can precisely localize the crucial regions in segmentation target while preserving the overall semantic consistency. We conduct a series of experiments with two cross-modality adaptation tasks, i,e. cardiac substructure and abdominal multi-organ segmentation. Experimental results indicate that our method achieves state-of-the-art performance in both tasks.

📄 PDF Abstract BibTeX arXiv:2205.11888

Code (0)

등록된 구현이 없습니다.

Tasks

Cardiac SegmentationDisentanglementImage SegmentationMedical Image SegmentationOrgan SegmentationSemantic SegmentationStyle Transfer

Similar Papers 제목 키워드 기반

Recovering Global Data Distribution Locally in Federated Learning

2024-09-21 · Ziyu Yao

Federated Learning (FL) is a distributed machine learning paradigm that enables collaboration among multiple clients to train a shared model without sharing raw data. However, a major challenge in FL is the label imbalan…

Federated Learningimage-classificationImage ClassificationImage Generation

DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model

2024-10-22 · Zhixiong Nan, Xianghong Li, Tao Xiang, Jifeng Dai

This paper is motivated by an interesting phenomenon: the performance of object detection lags behind that of instance segmentation (i.e., performance imbalance) when investigating the intermediate results from the begin…

DecoderInstance SegmentationObjectobject-detection+3

Federated Class-Incremental Learning

2022-03-22 · CVPR 2022 1 · Jiahua Dong, Lixu Wang, Zhen Fang, Gan Sun 외

Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume object classes of the overall framework are …

class-incremental learningClass Incremental LearningFederated LearningIncremental Learning

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

2018-11-12 · Jun Wen, Risheng Liu, Nenggan Zheng, Qian Zheng 외

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature align…

Domain AdaptationUnsupervised Domain Adaptation

Unsupervised Domain Adaptation With Imbalanced Cross-Domain Data

2015-12-01 · ICCV 2015 12 · Tzu Ming Harry Hsu, Wei Yu Chen, Cheng-An Hou, Yao-Hung Hubert Tsai 외

We address a challenging unsupervised domain adaptation problem with imbalanced cross-domain data. For standard unsupervised domain adaptation, one typically obtains labeled data in the source domain and only observes un…

Domain AdaptationGeneral ClassificationUnsupervised Domain Adaptation