56 citations · 123 across the 22 of their papers we have counts for
22 papers
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…
DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis
Pan Wang, Qiang Zhou, Yawen Wu +2
Multimodal Sentiment Analysis (MSA) leverages heterogeneous modalities, such as language, vision, and audio, to enhance the understanding of human sentiment. While existing models…
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…
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…
Rethinking Medical Anomaly Detection in Brain MRI: An Image Quality Assessment Perspective
Zixuan Pan, Jun Xia, Zheyu Yan +7
Reconstruction-based methods, particularly those leveraging autoencoders, have been widely adopted for anomaly detection task in brain MRI. Unlike most existing works try to improv…
Achieve Fairness without Demographics for Dermatological Disease Diagnosis
Ching-Hao Chiu, Yu-Jen Chen, Yawen Wu +2
In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and po…
EdgeOL: Efficient in-situ Online Learning on Edge Devices
Sheng Li, Geng Yuan, Yue Dai +10
Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-i…
Additional Positive Enables Better Representation Learning for Medical Images
Dewen Zeng, Yawen Wu, Xinrong Hu +3
This paper presents a new way to identify additional positive pairs for BYOL, a state-of-the-art (SOTA) self-supervised learning framework, to improve its representation learning a…
Self-supervised On-device Federated Learning from Unlabeled Streams
Jiahe Shi, Yawen Wu, Dewen Zeng +3
The ubiquity of edge devices has led to a growing amount of unlabeled data produced at the edge. Deep learning models deployed on edge devices are required to learn from these unla…
Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream
Yue Tang, Yawen Wu, Peipei Zhou +1
Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for…
Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis
Yawen Wu, Dewen Zeng, Zhepeng Wang +5
In dermatological disease diagnosis, the private data collected by mobile dermatology assistants exist on distributed mobile devices of patients. Federated learning (FL) can use de…
Achieving Fairness in Dermatological Disease Diagnosis through Automatic Weight Adjusting Federated Learning and Personalization
Gelei Xu, Yawen Wu, Jingtong Hu +1
Dermatological diseases pose a major threat to the global health, affecting almost one-third of the world's population. Various studies have demonstrated that early diagnosis and i…
Distributed Contrastive Learning for Medical Image Segmentation
Yawen Wu, Dewen Zeng, Zhepeng Wang +2
Supervised deep learning needs a large amount of labeled data to achieve high performance. However, in medical imaging analysis, each site may only have a limited amount of data an…
Federated Contrastive Learning for Volumetric Medical Image Segmentation
Yawen Wu, Dewen Zeng, Zhepeng Wang +2
Supervised deep learning needs a large amount of labeled data to achieve high performance. However, in medical imaging analysis, each site may only have a limited amount of data an…
FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis
Yawen Wu, Dewen Zeng, Xiaowei Xu +2
Many works have shown that deep learning-based medical image classification models can exhibit bias toward certain demographic attributes like race, gender, and age. Existing bias…
The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices
Yi Sheng, Junhuan Yang, Yawen Wu +5
Along with the progress of AI democratization, neural networks are being deployed more frequently in edge devices for a wide range of applications. Fairness concerns gradually emer…
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning
Yawen Wu, Dewen Zeng, Zhepeng Wang +5
Deep learning models have been deployed in an increasing number of edge and mobile devices to provide healthcare. These models rely on training with a tremendous amount of labeled…
Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning
Yawen Wu, Zhepeng Wang, Dewen Zeng +2
Contrastive learning (CL), a self-supervised learning approach, can effectively learn visual representations from unlabeled data. Given the CL training data, generative models can…
Decentralized Unsupervised Learning of Visual Representations
Yawen Wu, Zhepeng Wang, Dewen Zeng +3
Collaborative learning enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing collaborative lear…
Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast
Yawen Wu, Zhepeng Wang, Dewen Zeng +2
After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy. Contrastive learning has demonstrated it…
Positional Contrastive Learning for Volumetric Medical Image Segmentation
Dewen Zeng, Yawen Wu, Xinrong Hu +6
The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because o…
Energy Harvesting Powered Embedded Systems
Yawen Wu, Zhenge Jia, Jingtong Hu
Historically, battery is the power source for mobile, embedded and remote system applications. However, the development of battery techniques does not follow the Moore's Law. The l…