As is well known, military operation in a combat scenario is extremely intricate and often
prone to optimal and real-time decisions. In this paper, we study task management and …

Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible
FLOPs increase. However, the performance increase can not match the significantly …

基于嵌入式平台对深度神经网络轻量化的需求, 结合模块化, 逐层处理思想, 以主流检测识别深度
神经网络Faster RCNN 轻量化为目标, 设计基于深度稀疏低秩分解的轻量化方法. 针对Faster …

We studied the quantization of neural networks for their compression and representation
without retraining. The goal is to facilitate neural network representation and deployment in …

Deep neural networks have shown phenomenal performance in many domains including
computer vision, speech recognition, and self-driving cars in recent years. Deep learning …

O aprendizado de máquinas e o aprendizado profundo são utilizados para a resolução de
diversos problemas, em diferentes áreas de atuação. Esse fato impulsiona o …