no code implementations • 14 Dec 2023 • Tao Hu, Honglong Zhang, Fan Zeng, Min Du, XiangKun Du, Yue Zheng, Quanqi Li, Mengran Zhang, Dan Yang, Jihao Wu
However, temporal and spatial dimensions are extremely critical in the logistics field, and this limitation may directly affect the precision of subsidy and pricing strategies.
1 code implementation • 17 Nov 2023 • Tao Wang, Yuanbin Chen, Xinlin Zhang, Yuanbo Zhou, Junlin Lan, Bizhe Bai, Tao Tan, Min Du, Qinquan Gao, Tong Tong
Inspired by semi-supervised algorithms that use both labeled and unlabeled data for training, we propose the PLGDF framework, which builds upon the mean teacher network for segmenting medical images with less annotation.
1 code implementation • 29 Jun 2023 • Tao Wang, Xinlin Zhang, Yuanbo Zhou, Junlin Lan, Tao Tan, Min Du, Qinquan Gao, Tong Tong
To address this limitation, we propose an AL-based method that can be simultaneously applied to 2D medical image classification, segmentation, and 3D medical image segmentation tasks.
1 code implementation • 17 Nov 2022 • Brody Kutt, Pralay Ramteke, Xavier Mignot, Pamela Toman, Nandini Ramanan, Sujit Rokka Chhetri, Shan Huang, Min Du, William Hewlett
CCP unifies semi-supervised learning and noisy label learning for the goal of reliably outperforming a supervised baseline in any data scenario.
no code implementations • 29 Jan 2021 • Min Du, Luis C. Ho, Victor P. Debattista, Annalisa Pillepich, Dylan Nelson, Lars Hernquist, Rainer Weinberger
In observations, both bulge- and halo-dominated galaxies are likely to be classified as early-type galaxies with compact morphology and quiescent star formation.
Astrophysics of Galaxies
no code implementations • 13 Dec 2020 • Kun Zhang, Rui Wu, Ping Yao, Kai Deng, Ding Li, Renbiao Liu, Chuanguang Yang, Ge Chen, Min Du, Tianyao Zheng
We note that 2D pose estimation task is highly dependent on the contextual relationship between image patches, thus we introduce a self-supervised method for pretraining 2D pose estimation networks.
1 code implementation • 12 Oct 2020 • Min Du, Nesime Tatbul, Brian Rivers, Akhilesh Kumar Gupta, Lucas Hu, Wei Wang, Ryan Marcus, Shengtian Zhou, Insup Lee, Justin Gottschlich
Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task.
1 code implementation • 28 Nov 2019 • Jierui Lin, Min Du, Jian Liu
Although the incentive model for federated learning has not been fully developed, it is supposed that participants are able to get rewards or the privilege to use the final global model, as a compensation for taking efforts to train the model.
no code implementations • 24 Nov 2019 • Jinyin Chen, Jian Zhang, Zhi Chen, Min Du, Qi Xuan
In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP).
no code implementations • ICLR 2020 • Min Du, Ruoxi Jia, Dawn Song
In this paper, we demonstrate that applying differential privacy can improve the utility of outlier detection and novelty detection, with an extension to detect poisoning samples in backdoor attacks.
no code implementations • 23 Oct 2019 • Shaojin Cai, Yuyang Xue3 Qinquan Gao, Min Du, Gang Chen, Hejun Zhang, Tong Tong
It is not necessary for an expert to pick a representative reference slide in the proposed TAN method.
no code implementations • 11 Sep 2019 • Kun Zhang, Peng He, Ping Yao, Ge Chen, Rui Wu, Min Du, Huimin Li, Li Fu, Tianyao Zheng
Specifically, RAM learns a group of weights to represent the different importance of feature maps across resolutions, and the GPR gradually merges every two feature maps from low to high resolutions to regress final human keypoint heatmaps.
1 code implementation • 2 Aug 2019 • Wenbo Guo, Lun Wang, Xinyu Xing, Min Du, Dawn Song
As such, given a deep neural network model and clean input samples, it is very challenging to inspect and determine the existence of a trojan backdoor.
2 code implementations • 13 May 2018 • Qi-Zhi Cai, Min Du, Chang Liu, Dawn Song
The existence of adversarial examples hinders such applications.