A new two-stage object detection network without RoI-Pooling

  • Chao Yan
  • , Weihai Chen*
  • , Peter C.Y. Chen
  • , Amezquita S. Kendrick
  • , Xingming Wu
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Two-stage object detection networks often propose a set of candidate boxes in the first stage, and then fine- tune the boxes in the second stage. The original two-stage object detection methods mostly process the features among the candidate boxes in the picture by RoI-Pooling [3]. Due to the overlaps of the candidate boxes proposed in the first stage, the calculation of the second stage is repetitive and the single-frame detection is slow. RoI-Pooling also makes the features of the elongated shape deformed. In this paper, we present a new two-step object detection network, called Spatial Alignment Network(SAN), which does not use the RoI-Pooling layer and reduces the computational repeatability of the second stage. We also use atrous convolution for the network fine-tuning. Our network has a competitive result, and faster than the original two-stage detectors.

Original languageEnglish
Title of host publicationProceedings of the 30th Chinese Control and Decision Conference, CCDC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1680-1685
Number of pages6
ISBN (Electronic)9781538612439
DOIs
StatePublished - 6 Jul 2018
Event30th Chinese Control and Decision Conference, CCDC 2018 - Shenyang, China
Duration: 9 Jun 201811 Jun 2018

Publication series

NameProceedings of the 30th Chinese Control and Decision Conference, CCDC 2018

Conference

Conference30th Chinese Control and Decision Conference, CCDC 2018
Country/TerritoryChina
CityShenyang
Period9/06/1811/06/18

Keywords

  • Computer Vision
  • Deep Learning
  • Object Detection

Fingerprint

Dive into the research topics of 'A new two-stage object detection network without RoI-Pooling'. Together they form a unique fingerprint.

Cite this