Search Results for author: Yiwen Ye

Found 14 papers, 9 papers with code

Meta Curvature-Aware Minimization for Domain Generalization

no code implementations16 Dec 2024 Ziyang Chen, Yiwen Ye, Feilong Tang, Yongsheng Pan, Yong Xia

However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization.

Domain Generalization Meta-Learning

CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentation

no code implementations15 Nov 2024 Yihang Fu, Ziyang Chen, Yiwen Ye, Xingliang Lei, Zhisong Wang, Yong Xia

Existing SAM-based approaches attempt to address the need for manual prompts by introducing prompt generators that automatically generate these prompts.

Domain Generalization Image Segmentation +2

Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation

no code implementations17 Oct 2024 Ziyang Chen, Yiwen Ye, Yongsheng Pan, Jingfeng Zhang, Yanning Zhang, Yong Xia

To facilitate adaptation while preserving data privacy, source-free domain adaptation (SFDA) and test-time adaptation (TTA) have emerged as effective paradigms, relying solely on target domain data.

Image Segmentation Medical Image Segmentation +4

MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model

1 code implementation8 Oct 2024 Yiwen Ye, Ziyang Chen, Jianpeng Zhang, Yutong Xie, Yong Xia

In this paper, we introduce MedUniSeg, a prompt-driven universal segmentation model designed for 2D and 3D multi-task segmentation across diverse modalities and domains.

Image Segmentation Medical Image Segmentation +2

Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation

1 code implementation14 Aug 2024 Ziyang Chen, Yiwen Ye, Yongsheng Pan, Yong Xia

Extensive experiments establish the effectiveness of the proposed gradient alignment and dynamic learning rate and substantiate the superiority of our GraTa method over other state-of-the-art TTA methods on a benchmark medical image segmentation task.

Image Segmentation Medical Image Segmentation +2

Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation

1 code implementation CVPR 2024 Ziyang Chen, Yongsheng Pan, Yiwen Ye, Mengkang Lu, Yong Xia

Distribution shift widely exists in medical images acquired from different medical centres and poses a significant obstacle to deploying the pre-trained semantic segmentation model in real-world applications.

Image Segmentation Medical Image Segmentation +2

Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning

1 code implementation CVPR 2024 Yiwen Ye, Yutong Xie, Jianpeng Zhang, Ziyang Chen, Qi Wu, Yong Xia

In this paper, we reconsider versatile self-supervised learning from the perspective of continual learning and propose MedCoSS, a continuous self-supervised learning approach for multi-modal medical data.

Continual Learning Continual Self-Supervised Learning +3

Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation

1 code implementation31 May 2023 Ziyang Chen, Yongsheng Pan, Yiwen Ye, Hengfei Cui, Yong Xia

In this paper, we propose a multi-source DG method called Treasure in Distribution (TriD), which constructs an unprecedented search space to obtain the model with strong robustness by randomly sampling from a uniform distribution.

Domain Generalization Image Segmentation +2

UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner

1 code implementation7 Apr 2023 Yiwen Ye, Yutong Xie, Jianpeng Zhang, Ziyang Chen, Yong Xia

Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation.

Decoder Image Segmentation +3

Boundary-Aware Network for Kidney Parsing

1 code implementation29 Aug 2022 Shishuai Hu, Yiwen Ye, Zehui Liao, Yong Xia

Although numerous deep learning models have achieved remarkable success in many medical image segmentation tasks, accurate segmentation of kidney structures on computed tomography angiography (CTA) images remains challenging, due to the variable sizes of kidney tumors and the ambiguous boundaries between kidney structures and their surroundings.

Decoder Image Segmentation +3

Cannot find the paper you are looking for? You can Submit a new open access paper.