Title: Accelerates inference by separable max-pooling for object detection

Authors: Zhen Yang; Zhikui Ouyang; Fan Yang; Zhijian Yin

Addresses: School of Communication and Electronics, Jiangxi Science and Technology Normal University, Nanchang, 330038, China ' School of Communication and Electronics, Jiangxi Science and Technology Normal University, Nanchang, 330038, China ' School of Communication and Electronics, Jiangxi Science and Technology Normal University, Nanchang, 330038, China ' School of Communication and Electronics, Jiangxi Science and Technology Normal University, Nanchang, 330038, China

Abstract: The object detector can achieve better performance, but it also requires high computational cost. In this work, we present an accelerated inference in the structure spatial pyramid pooling (SPP), called ACSPP, based on an optimised architecture that uses combinational separable max-pooling to replace the standard max-pooling operator, and apply it to the YOLOX model. For the MS COCO Val dataset, the average inference time the proposed ACSPP is 10.87 ms, while the average inference time of the YOLOX model is 12.46 ms when a single NVIDIA 1660ti GPU is used. For the Pascal VOC2007 val dataset, the average inference time of the proposed ACSPP is 33.35 ms, while the average inference time of the YOLOX model is 37.30 ms when a single NVIDIA 1050ti GPU is used.

Keywords: neutral network; object detection; YOLOX; deep learning; ACSPP.

DOI: 10.1504/IJSCIP.2022.129573

International Journal of System Control and Information Processing, 2022 Vol.4 No.1, pp.43 - 55

Received: 10 Nov 2021
Accepted: 16 Jun 2022
Published online: 14 Mar 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article