HIGHLIGHTS
- who: Giosuu00e9 Cataldo Marinu00f3 from the Dipartimento di Informatica, Universitu00e0 degli Studi di Milano, Via Celoria, Milano, Italy have published the research work: Deep neural networks compression: A comparative survey and choice recommendations, in the Journal: (JOURNAL)
- what: The authors propose the first extensive comparison to the best of the knowledge of the main lossy and structure-preserving approaches to compress pre-trained CNNs applicable in principle to any existing model. The study is intended to provide a first and preliminary guidance to choose the most suitable compression technique when there is the need to . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.