3 papers
cs.CV2024
Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation
Minh-Tuan Tran, Trung Le, Xuan-May Le +3
Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data.…
cs.CV2024
Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
Minh-Tuan Tran, Trung Le, Xuan-May Le +2
Federated Class-Incremental Learning (FCIL) is an underexplored yet pivotal issue, involving the dynamic addition of new classes in the context of federated learning. In this field…
cond-mat.mtrl-sci2023
Theory of transition from brittle to ductile fracture
Khanh Chau Le, Hyeonyeong Jeong, Tuan Minh Tran
In this paper, two improvements to the theory of transition from brittle to ductile fracture developed by Langer are proposed. First, considering the drastic temperature rise near…