Selective Multi-Scale Learning for Object Detection

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better a...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Chen, Junliang, Lu, Weizeng, Shen, Linlin
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 16.06.2022
Subjects
Detectors
Learning
Networks
Object recognition
Online AccessGet full text

Cover

More Information
Summary:Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8\% improvement in AP (from 39.1\% to 40.9\%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0\% improvement in AP.
ISSN:2331-8422