University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Association Loss for Visual Object Detection

Xu, Dongli, Guan, Jian, Feng, Pengming and Wang, Wenwu (2020) Association Loss for Visual Object Detection IEEE Signal Processing Letters.

XuGFW_SPL_2020.pdf - Accepted version Manuscript

Download (14MB) | Preview


Convolutional neural network (CNN) is a popular choice for visual object detection where two sub-nets are often used to achieve object classification and localization separately. However, the intrinsic relation between the localization and classification sub-nets was not exploited explicitly for object detection. In this letter, we propose a novel association loss, namely, the proxy squared error (PSE) loss, to entangle the two sub-nets, thus use the dependency between the classification and localization scores obtained from these two sub-nets to improve the detection performance. We evaluate our proposed loss on the MS-COCO dataset and compare it with the loss in a recent baseline, i.e. the fully convolutional one-stage (FCOS) detector. The results show that our method can improve the AP from 33:8 to 35:4 and AP75 from 35:4 to 37:8, as compared with the FCOS baseline.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Xu, Dongli
Guan, Jian
Feng, Pengming
Date : 24 July 2020
Uncontrolled Keywords : Association loss, object detection, object localization, object classification, convolutional neural networks
Additional Information : Embargo OK Metadata Pending
Depositing User : James Marshall
Date Deposited : 27 Jul 2020 12:54
Last Modified : 27 Jul 2020 12:54

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800