Object detectors involving a NAS-gate convolutional module and capsule attention module

Thanaporn Viriyasaranon, Jang Hwan Choi

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

Several state-of-the-art object detectors have demonstrated outstanding performances by optimizing feature representation through modification of the backbone architecture and exploitation of a feature pyramid. To determine the effectiveness of this approach, we explore the modification of object detectors’ backbone and feature pyramid by utilizing Neural Architecture Search (NAS) and Capsule Network. We introduce two modules, namely, NAS-gate convolutional module and Capsule Attention module. The NAS-gate convolutional module optimizes standard convolution in a backbone network based on differentiable architecture search cooperation with multiple convolution conditions to overcome object scale variation problems. The Capsule Attention module exploits the strong spatial relationship encoding ability of the capsule network to generate a spatial attention mask, which emphasizes important features and suppresses unnecessary features in the feature pyramid, in order to optimize the feature representation and localization capability of the detectors. Experimental results indicate that the NAS-gate convolutional module can alleviate the object scale variation problem and the Capsule Attention network can help to avoid inaccurate localization. Next, we introduce NASGC-CapANet, which incorporates the two modules, i.e., a NAS-gate convolutional module and capsule attention module. Results of comparisons against state-of-the-art object detectors on the MS COCO val-2017 dataset demonstrate that NASGC-CapANet-based Faster R-CNN significantly outperforms the baseline Faster R-CNN with a ResNet-50 backbone and a ResNet-101 backbone by mAPs of 2.7% and 2.0%, respectively. Furthermore, the NASGC-CapANet-based Cascade R-CNN achieves a box mAP of 43.8% on the MS COCO test-dev dataset.

Original languageEnglish
Article number3916
JournalScientific Reports
Volume12
Issue number1
DOIs
StatePublished - Dec 2022

Bibliographical note

Funding Information:
This work was partly supported by a grant from National R&D Project of “Development of automatic screening and hybrid detection system for hazardous material detecting in port container (20200611)”, the Technology development Program of MSS [S3146559], the National Research Foundation of Korea (NRF) grants funded by the Korean government (MSIT) (No. NRF-2020R1A4A1016619), and by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: KMDF_PR_20200901_0016, 9991006689). The funders had no role in study design, data collection and analysis, decision to publish, or manuscript preparation.

Publisher Copyright:
© 2022, The Author(s).

Fingerprint

Dive into the research topics of 'Object detectors involving a NAS-gate convolutional module and capsule attention module'. Together they form a unique fingerprint.

Cite this