3 citations · 6 across the 8 of their papers we have counts for
6 papers · 1 filter
Post-Deployment Adaptation with Access to Source Data via Federated Learning and Source-Target Remote Gradient Alignment
Felix Wagner, Zeju Li, Pramit Saha +1
Deployment of Deep Neural Networks in medical imaging is hindered by distribution shift between training data and data processed after deployment, causing performance degradation.…
Context Label Learning: Improving Background Class Representations in Semantic Segmentation
Zeju Li, Konstantinos Kamnitsas, Cheng Ouyang +2
Background samples provide key contextual information for segmenting regions of interest (ROIs). However, they always cover a diverse set of structures, causing difficulties for th…
Improved post-hoc probability calibration for out-of-domain MRI segmentation
Cheng Ouyang, Shuo Wang, Chen Chen +4
Probability calibration for deep models is highly desirable in safety-critical applications such as medical imaging. It makes output probabilities of deep networks interpretable, b…
Tackling Long-Tailed Category Distribution Under Domain Shifts
Xiao Gu, Yao Guo, Zeju Li +5
Machine learning models fail to perform well on real-world applications when 1) the category distribution P(Y) of the training dataset suffers from long-tailed distribution and 2)…
Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores
Zeju Li, Konstantinos Kamnitsas, Mobarakol Islam +2
Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift.…
Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
Cheng Ouyang, Chen Chen, Surui Li +4
Deep learning models usually suffer from domain shift issues, where models trained on one source domain do not generalize well to other unseen domains. In this work, we investigate…