Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters

Harim Jung, Myeong Seok Oh, Cheoljong Yang, Seong Whan Lee

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

Abstract

Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. However, image classification and object detection are essentially different tasks and there is no guarantee that the optimal backbone for classification is also optimal for object detection. Recent neural architecture search (NAS) research has demonstrated that automatically designing a backbone specifically for object detection helps improve the overall accuracy. In this paper, we introduce a neural architecture adaptation method that can optimize the given backbone for detection purposes, while still allowing the use of pre-trained parameters. We propose to adapt both the micro- and macro-architecture by searching for specific operations and the number of layers, in addition to the output channel dimensions of each block. It is important to find the optimal channel depth, as it greatly affects the feature representation capability and computation cost. We conduct experiments with our searched backbone for object detection and demonstrate that our backbone outperforms both manually designed and searched state-of-the-art backbones on the COCO dataset.

Original languageEnglish
Title of host publication2022 26th International Conference on Pattern Recognition, ICPR 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2393-2400
Number of pages8
ISBN (Electronic)9781665490627
DOIs
Publication statusPublished - 2022
Event26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canada
Duration: 2022 Aug 212022 Aug 25

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2022-August
ISSN (Print)1051-4651

Conference

Conference26th International Conference on Pattern Recognition, ICPR 2022
Country/TerritoryCanada
CityMontreal
Period22/8/2122/8/25

Bibliographical note

Funding Information:
This work was supported by NCSOFT, in part by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program (Korea University)).

Publisher Copyright:
© 2022 IEEE.

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters'. Together they form a unique fingerprint.

Cite this