Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Hulin, Li, Jun, Wei, Hanbing, Liu, Zheng, Zhan, Zhenfei, Ren, Qiliang
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2206.02424
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911939346563072
author Li, Hulin
Li, Jun
Wei, Hanbing
Liu, Zheng
Zhan, Zhenfei
Ren, Qiliang
author_facet Li, Hulin
Li, Jun
Wei, Hanbing
Liu, Zheng
Zhan, Zhenfei
Ren, Qiliang
contents Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, Slim-Neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP50 for the SODA10M at a speed of ~ 100FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv
format Preprint
id arxiv_https___arxiv_org_abs_2206_02424
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Slim-neck by GSConv: A lightweight-design for real-time detector architectures
Li, Hulin
Li, Jun
Wei, Hanbing
Liu, Zheng
Zhan, Zhenfei
Ren, Qiliang
Computer Vision and Pattern Recognition
Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, Slim-Neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP50 for the SODA10M at a speed of ~ 100FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv
title Slim-neck by GSConv: A lightweight-design for real-time detector architectures
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2206.02424