79 citations · 156 across the 15 of their papers we have counts for
16 papers
Defending Against Poisoning Attacks in Federated Learning with Blockchain
Nanqing Dong, Zhipeng Wang, Jiahao Sun +3
In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learnin…
FLock: Defending Malicious Behaviors in Federated Learning with Blockchain
Nanqing Dong, Jiahao Sun, Zhipeng Wang +2
Federated learning (FL) is a promising way to allow multiple data owners (clients) to collaboratively train machine learning models without compromising data privacy. Yet, existing…
Label-Efficient Object Detection via Region Proposal Network Pre-Training
Nanqing Dong, Linus Ericsson, Yongxin Yang +2
Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies foc…
Learning Underrepresented Classes from Decentralized Partially Labeled Medical Images
Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu
Using decentralized data for federated training is one promising emerging research direction for alleviating data scarcity in the medical domain. However, in contrast to large-scal…
Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity
Nanqing Dong, Jiayi Wang, Irina Voiculescu
Due to the high human cost of annotation, it is non-trivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenie…
Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
Zhaoming Qin, Nanqing Dong, Di Liu +2
As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. However, centralized…
Federated Contrastive Learning for Decentralized Unlabeled Medical Images
Nanqing Dong, Irina Voiculescu
A label-efficient paradigm in computer vision is based on self-supervised contrastive pre-training on unlabeled data followed by fine-tuning with a small number of labels. Making p…
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images
Nanqing Dong, Matteo Maggioni, Yongxin Yang +3
This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals,…
Negational Symmetry of Quantum Neural Networks for Binary Pattern Classification
Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu +1
Entanglement is a physical phenomenon, which has fueled recent successes of quantum algorithms. Although quantum neural networks (QNNs) have shown promising results in solving simp…
Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data
Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang +3
The data-driven nature of deep learning (DL) models for semantic segmentation requires a large number of pixel-level annotations. However, large-scale and fully labeled medical dat…
Adversarial Domain Adaptation Being Aware of Class Relationships
Zeya Wang, Baoyu Jing, Yang Ni +3
Adversarial training is a useful approach to promote the learning of transferable representations across the source and target domains, which has been widely applied for domain ada…
Toward Understanding the Impact of Staleness in Distributed Machine Learning
Wei Dai, Yi Zhou, Nanqing Dong +2
Many distributed machine learning (ML) systems adopt the non-synchronous execution in order to alleviate the network communication bottleneck, resulting in stale parameters that do…
Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-slide Images
Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang +3
Convolutional neural networks have led to significant breakthroughs in the domain of medical image analysis. However, the task of breast cancer segmentation in whole-slide images (…
Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio
Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang +3
The cardiothoracic ratio (CTR), a clinical metric of heart size in chest X-rays (CXRs), is a key indicator of cardiomegaly. Manual measurement of CTR is time-consuming and can be a…
ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang +2
Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires…
SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays
Wei Dai, Joseph Doyle, Xiaodan Liang +4
Chest X-ray (CXR) is one of the most commonly prescribed medical imaging procedures, often with over 2-10x more scans than other imaging modalities such as MRI, CT scan, and PET sc…