University of Leicester
Browse
elsarticle-template.pdf (5.44 MB)

SWIPENET: Object detection in noisy underwater scenes

Download (5.44 MB)
journal contribution
posted on 2022-08-08, 11:09 authored by L Chen, F Zhou, S Wang, J Dong, N Li, H Ma, X Wang, Huiyu Zhou

Deep learning based object detection methods have achieved promising performance in controlled environments. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) images in the underwater datasets and real applications are blurry whilst accompanying severe noise that confuses the detectors and (2) objects in real applications are usually small. In this paper, we propose a Sample-WeIghted hyPEr Network (SWIPENET), and a novel training paradigm named Curriculum Multi-Class Adaboost (CMA), to address these two problems at the same time. Firstly, the backbone of SWIPENET produces multiple high resolution and semantic-rich Hyper Feature Maps, which significantly improve small object detection. Secondly, inspired by the human education process that drives the learning from easy to hard concepts, we propose the noise-robust CMA training paradigm that learns the clean data first and then move on to learns the diverse noisy data. Experiments on four underwater object detection datasets show that the proposed SWIPENET+CMA framework achieves better or competitive accuracy in object detection against several state-of-the-art approaches.

Funding

Zhejiang Provincial Natural Science Foundation of China under Grant No. LY19F030011

History

Author affiliation

School of Computing and Mathematical Sciences, University of Leicester

Version

  • AM (Accepted Manuscript)

Published in

Pattern Recognition

Volume

132

Publisher

Elsevier

issn

0031-3203

Acceptance date

2022-07-21

Copyright date

2022

Available date

2023-07-23

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC