싱글숏 멀티박스 검출기에서 객체 검출을 위한 가속 회로 인지형 가지치기 기반 합성곱 신경망 기법 (Convolutional Neural Network Based on Accelerator-Aware Pruning for Object Detection in Single-Shot Multibox Detector)

서지정보

· 발행기관 : 한국정보통신학회
· 수록지 정보 : 한국정보통신학회논문지 / 24권 / 1호 / 141 ~ 144페이지
· 저자명 : 강형주

초록

Convolutional neural networks (CNNs) show high performance in computer vision tasks including object detection, but a lot of weight storage and computation is required. In this paper, a pruning scheme is applied to CNNs for object detection, which can remove much amount of weights with a negligible performance degradation.
Contrary to the previous ones, the pruning scheme applied in this paper considers the base accelerator architecture.
With the consideration, the pruned CNNs can be efficiently performed on an ASIC or FPGA accelerator. Even with the constrained pruning, the resulting CNN shows a negligible degradation of detection performance, less-than1% point degradation of mAP on VOD0712 test set. With the proposed scheme, CNNs can be applied to objection dtection efficiently.

영어초록

Convolutional neural networks (CNNs) show high performance in computer vision tasks including object detection, but a lot of weight storage and computation is required. In this paper, a pruning scheme is applied to CNNs for object detection, which can remove much amount of weights with a negligible performance degradation.
Contrary to the previous ones, the pruning scheme applied in this paper considers the base accelerator architecture.
With the consideration, the pruned CNNs can be efficiently performed on an ASIC or FPGA accelerator. Even with the constrained pruning, the resulting CNN shows a negligible degradation of detection performance, less-than1% point degradation of mAP on VOD0712 test set. With the proposed scheme, CNNs can be applied to objection dtection efficiently.

참고자료

· 없음