1 code implementation • 15 Jun 2023 • Binhang Qi, Hailong Sun, Hongyu Zhang, Ruobing Zhao, Xiang Gao
In this paper, we propose a novel approach that incorporates modularization into the model training process, i. e., modularizing-while-training (MwT).
1 code implementation • 1 Apr 2023 • Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang, Zhaotian Li, Xudong Liu
Prior approaches to DNN model reuse have two main limitations: 1) reusing the entire model, while only a small part of the model's functionalities (labels) are required, would cause much overhead (e. g., computational and time costs for inference), and 2) model reuse would inherit the defects and weaknesses of the reused model, and hence put the new system under threats of security attack.
1 code implementation • 11 Sep 2022 • Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang
To patch a weak CNN model that performs unsatisfactorily on a target class (TC), we compose the weak CNN model with the corresponding module obtained from a strong CNN model.
