Saved in:
Bibliographic Details
Main Authors: Wang, Jiawen, Chen, Yinda, Liu, Xiaoyu, Liu, Che, Liu, Dong, Gao, Jianqing, Xiong, Zhiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.12008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911060199473152
author Wang, Jiawen
Chen, Yinda
Liu, Xiaoyu
Liu, Che
Liu, Dong
Gao, Jianqing
Xiong, Zhiwei
author_facet Wang, Jiawen
Chen, Yinda
Liu, Xiaoyu
Liu, Che
Liu, Dong
Gao, Jianqing
Xiong, Zhiwei
contents Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the theoretical analysis, which leads to a superficial understanding of masked reconstruction and insufficient exploitation of its potential in enhancing feature extraction and representation learning. In this paper, we reframe masked reconstruction as a sparse signal reconstruction problem and theoretically prove that the dual form of complementary masks possesses superior capabilities in extracting domain-agnostic image features. Based on this compelling insight, we propose MaskTwins, a simple yet effective UDA framework that integrates masked reconstruction directly into the main training pipeline. MaskTwins uncovers intrinsic structural patterns that persist across disparate domains by enforcing consistency between predictions of images masked in complementary ways, enabling domain generalization in an end-to-end manner. Extensive experiments verify the superiority of MaskTwins over baseline methods in natural and biological image segmentation. These results demonstrate the significant advantages of MaskTwins in extracting domain-invariant features without the need for separate pre-training, offering a new paradigm for domain-adaptive segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12008
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual form Complementary Masking for Domain-Adaptive Image Segmentation
Wang, Jiawen
Chen, Yinda
Liu, Xiaoyu
Liu, Che
Liu, Dong
Gao, Jianqing
Xiong, Zhiwei
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the theoretical analysis, which leads to a superficial understanding of masked reconstruction and insufficient exploitation of its potential in enhancing feature extraction and representation learning. In this paper, we reframe masked reconstruction as a sparse signal reconstruction problem and theoretically prove that the dual form of complementary masks possesses superior capabilities in extracting domain-agnostic image features. Based on this compelling insight, we propose MaskTwins, a simple yet effective UDA framework that integrates masked reconstruction directly into the main training pipeline. MaskTwins uncovers intrinsic structural patterns that persist across disparate domains by enforcing consistency between predictions of images masked in complementary ways, enabling domain generalization in an end-to-end manner. Extensive experiments verify the superiority of MaskTwins over baseline methods in natural and biological image segmentation. These results demonstrate the significant advantages of MaskTwins in extracting domain-invariant features without the need for separate pre-training, offering a new paradigm for domain-adaptive segmentation.
title Dual form Complementary Masking for Domain-Adaptive Image Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.12008