no code implementations • 13 Feb 2024 • Degan Hao, Dooman Arefan, Margarita Zuley, Wendie Berg, Shandong Wu
It is essential to develop deep learning models that are robust to adversarial data while accurate on standard, clean data.
1 code implementation • ICCV 2023 • Guangyu Sun, Matias Mendieta, Jun Luo, Shandong Wu, Chen Chen
Personalized Federated Learning (PFL) represents a promising solution for decentralized learning in heterogeneous data environments.
no code implementations • 2 Feb 2023 • Zhengbo Zhou, Jun Luo, Dooman Arefan, Gene Kitamura, Shandong Wu
Curriculum learning is a learning method that trains models in a meaningful order from easier to harder samples.
1 code implementation • ICCV 2023 • Jun Luo, Matias Mendieta, Chen Chen, Shandong Wu
Based on our observation, in this work, we propose Personalized Global Federated Learning (PGFed), a novel personalized FL framework that enables each client to personalize its own global objective by explicitly and adaptively aggregating the empirical risks of itself and other clients.
no code implementations • 15 Nov 2022 • Saba Dadsetan, Mohsen Hejrati, Shandong Wu, Somaye Hashemifar
We also show that pretraining on extended (but not labeled) brain MRI data outperforms pretraining on natural images.
no code implementations • 20 Nov 2021 • Long Gao, Chang Liu, Dooman Arefan, Ashok Panigrahy, Margarita L. Zuley, Shandong Wu
To address this challenge, we propose a medical-knowledge-guided one-class classification approach that leverages domain-specific knowledge of classification tasks to boost the model's performance.
no code implementations • 20 Nov 2021 • Long Gao, Chang Liu, Dooman Arefan, Ashok Panigrahy, Shandong Wu
These methods mainly focus on capturing either compact or descriptive features, where the information of the samples of a given one class is not sufficiently utilized.
no code implementations • 21 Oct 2021 • Jun Luo, Dooman Arefan, Margarita Zuley, Jules Sumkin, Shandong Wu
In this work, we propose an end-to-end Curriculum Learning (CL) strategy in task space for classifying the three categories of Full-Field Digital Mammography (FFDM), namely Malignant, Negative, and False recall.
1 code implementation • 20 Oct 2021 • Jun Luo, Gene Kitamura, Dooman Arefan, Emine Doganay, Ashok Panigrahy, Shandong Wu
We evaluate our method through extensive experiments on a classification task of elbow fracture with a dataset of 1, 964 images.
no code implementations • 20 Oct 2021 • Jun Luo, Gene Kitamura, Emine Doganay, Dooman Arefan, Shandong Wu
We design an experiment with 1865 elbow X-ray images for a fracture/normal binary classification task and compare our proposed method to a baseline method and a previous method using multiple metrics.
2 code implementations • 15 Oct 2021 • Jun Luo, Shandong Wu
We also introduce a method to flexibly control the focus of training APPLE between global and local objectives.
no code implementations • 15 Oct 2021 • Jun Luo, Shandong Wu
Machine learning in medical research, by nature, needs careful attention on obeying the regulations of data privacy, making it difficult to train a machine learning model over gathered data from different medical centers.
no code implementations • 29 Sep 2021 • Jun Luo, Shandong Wu
We also introduce a method to flexibly control the focus of training APPLE between global and local objectives.