activity
20192025
most citedFederated Contrastive Learning for Volumetric Medical Image Segmentation

56 citations · 76 across the 14 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2025

Contrastive Learning with Diffusion Features for Weakly Supervised Medical Image Segmentation

Dewen Zeng, Xinrong Hu, Yu-Jen Chen +3

Weakly supervised semantic segmentation (WSSS) methods using class labels often rely on class activation maps (CAMs) to localize objects. However, traditional CAM-based methods str…

cs.CV2024

Enhancing 3D Transformer Segmentation Model for Medical Image with Token-level Representation Learning

Xinrong Hu, Dewen Zeng, Yawen Wu +2

In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without us…

cs.CV2024

Contrastive Learning with Synthetic Positives

Dewen Zeng, Yawen Wu, Xinrong Hu +2

Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instance…

cs.CV2024

Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis

Qingpeng Kong, Ching-Hao Chiu, Dewen Zeng +4

Numerous studies have revealed that deep learning-based medical image classification models may exhibit bias towards specific demographic attributes, such as race, gender, and age.…

cs.CV20212 cited

Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation

Xinrong Hu, Dewen Zeng, Xiaowei Xu +1

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotat…

cs.CV2021

Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography

Dewen Zeng, Mingqi Li, Yukun Ding +7

Most existing deep learning-based frameworks for image segmentation assume that a unique ground truth is known and can be used for performance evaluation. This is true for many app…