DWANet: Focus on Foreground Features for More Accurate Location

Jiwei Hu, Yuxing Zheng, Kin Man Lam, Ping Lou

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Object detection can locate objects in an image using bounding boxes, which can facilitate classification and image understanding, resulting in a wide range of applications. Knowing how to mine useful features from images and detect objects of different scales have become the focus for object-detection research. In this paper, considering the importance of foreground features in the process of object detection, a foreground feature extraction module, based on deformable convolution, is proposed, and the attention mechanism is integrated to suppress the interference from the background. To learn effective features, considering that different layers in a convolutional neural network have different contributions, we propose methods to learn the weights for feature fusion. Experiments on the VOC datasets and COCO datasets show that the proposed algorithm can effectively improve the object detection accuracy, which is 12.1% higher than Faster R-CNN, 1.5% higher than RefineDet, and 2.3% higher than the Hierarchical Shot Detector (HSD).

Original languageEnglish
Pages (from-to)30716-30729
Number of pages14
JournalIEEE Access
Volume10
DOIs
Publication statusPublished - Mar 2022

Keywords

  • feature fusion
  • foreground features
  • multi-scale
  • Object detection

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this