Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Jan-Henrik Lambrechts"'
Publikováno v:
CICC
Deep neural networks present a promising future in applications, ranging from face ID on mobile phones to self-driving cars. Weight pruning and quantization act as valuable solutions to release the burden of computation and memory. Figure 1 shows the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7031984a0acbbf4ddb8e5926782413b
https://doi.org/10.1109/cicc51472.2021.9431519
https://doi.org/10.1109/cicc51472.2021.9431519
Autor:
Kaisheng Ma, Hao Cheng, Jan-Henrik Lambrechts, Kaidi Xu, Huan Zhang, Xue Lin, Yanzhi Wang, Shaokai Ye, Sijia Liu, Aojun Zhou
Publikováno v:
ICCV
It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training can provide a notion of securi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::516c3d6f105f8469ff8435a0499a7b3b
https://doi.org/10.1109/iccv.2019.00020
https://doi.org/10.1109/iccv.2019.00020