Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Strack, Lukas"'
Different activation functions work best for different deep learning models. To exploit this, we leverage recent advancements in gradient-based search techniques for neural architectures to efficiently identify high-performing activation functions fo
Externí odkaz:
http://arxiv.org/abs/2408.06820
Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial patches, posing risks in its
Externí odkaz:
http://arxiv.org/abs/2309.15519