Towards Accurate One-Stage Object Detection With AP-Loss

Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Lingyu Duan, Zhibo Chen, Changwei He, Junni Zou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We verify good convergence property of the proposed algorithm theoretically and empirically. Experimental results demonstrate notable performance improvement in state-of-the-art one-stage detectors based on AP-loss over different kinds of classification-losses on various benchmarks, without changing the network architectures.

Original languageEnglish
Title of host publication2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages5114-5122
Number of pages9
ISBN (Electronic)9781728132938
DOIs
Publication statusPublished - 9 Jan 2020
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Publication series

NameIEEE/CVF Conference on Computer Vision and Pattern Recognition
ISSN (Electronic)2575-7075

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019
Abbreviated titleCVPR 2019
CountryUnited States
CityLong Beach
Period16/06/1920/06/19

Keywords

  • Categorization
  • Recognition: Detection
  • Retrieval

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Towards Accurate One-Stage Object Detection With AP-Loss'. Together they form a unique fingerprint.

Cite this