Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Patwari, Kartik"'
Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to a target domain using only unlabeled target data. Current SFDA methods face challenges in effectively leveraging pre-trained knowledge and exploiting target domain data.
Externí odkaz:
http://arxiv.org/abs/2405.18376
The increasing size of Deep Neural Networks (DNNs) poses a pressing need for model compression, particularly when employed on resource constrained devices. Concurrently, the susceptibility of DNNs to adversarial attacks presents another significant h
Externí odkaz:
http://arxiv.org/abs/2308.08160