UMS-ODNet: Unified-scale domain adaptation mechanism driven object detection network with multi-scale attention.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Unsupervised domain adaptation techniques improve the generalization capability and performance of detectors, especially when the source and target domains have different distributions. Compared with two-stage detectors, one-stage detectors (especially YOLO series) provide better real-time capabilities and become primary choices in industrial fields. In this paper, to improve cross-domain object detection performance, we propose a Unified-Scale Domain Adaptation Mechanism Driven Object Detection Network with Multi-Scale Attention (UMS-ODNet). UMS-ODNet chooses YOLOv6 as the basic framework in terms of its balance between efficiency and accuracy. UMS-ODNet considers the adaptation consistency across different scale feature maps, which tends to be ignored by existing methods. A unified-scale domain adaptation mechanism is designed to fully utilize and unify the discriminative information from different scales. A multi-scale attention module is constructed to further improve the multi-scale representation ability of features. A novel loss function is created to maintain the consistency of multi-scale information by considering the homology of the descriptions from the same latent feature. Multiply experiments are conducted on four widely used datasets. Our proposed method outperforms other state-of-the-art techniques, illustrating the feasibility and effectiveness of the proposed UMS-ODNet.

Authors

  • Yuze Li
    Disinfection and Supply Center, Liyang People's Hospital, Liyang 213300, Jiangsu, China.
  • Yan Zhang
    Affiliated Hospital of Liaoning University of Traditional Chinese Medicine, Shenyang, 110032, China.
  • Chunling Yang
    School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China. Electronic address: yangcl1@hit.edu.cn.
  • Yu Chen
    State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, Sichuan, China.