1 code implementation • 26 Mar 2024 • Qingyuan Wang, Barry Cardiff, Antoine Frappé, Benoit Larras, Deepu John
By searching and employing the most appropriate tiny model as the computational saver for a given large model, the proposed approaches work as a novel and generic method to model compression.
Ranked #163 on Image Classification on ImageNet
1 code implementation • 4 Mar 2024 • Qingyuan Wang, Barry Cardiff, Antoine Frappé, Benoit Larras, Deepu John
Moreover, most current dynamic compression designs are monolithic and tightly integrated with base models, thereby complicating the adaptation to novel base models.
no code implementations • 17 Oct 2023 • Guoxin Wang, Qingyuan Wang, Ganesh Neelakanta Iyer, Avishek Nag, Deepu John
Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks.
2 code implementations • 15 Sep 2023 • Shaowu Chen, Weize Sun, Lei Huang, Xiaopeng Li, Qingyuan Wang, Deepu John
In recent years, two competitive time series classification models, namely, ROCKET and MINIROCKET, have garnered considerable attention due to their low training cost and high accuracy.