PlumX Metrics
Embed PlumX Metrics

TIG-DETR: Enhancing Texture Preservation and Information Interaction for Target Detection

Applied Sciences (Switzerland), ISSN: 2076-3417, Vol: 13, Issue: 14
2023
  • 0
    Citations
  • 0
    Usage
  • 1
    Captures
  • 2
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Captures
    1
  • Mentions
    2
    • Blog Mentions
      1
      • Blog
        1
    • News Mentions
      1
      • 1

Most Recent News

New Information Technology Study Findings Recently Were Published by Researchers at Northeast Normal University (TIG-DETR: Enhancing Texture Preservation and Information Interaction for Target Detection)

2023 AUG 10 (NewsRx) -- By a News Reporter-Staff News Editor at Network Daily News -- Researchers detail new data in information technology. According to

Article Description

FPN (Feature Pyramid Network) and transformer-based target detectors are commonly employed in target detection tasks. However, these approaches suffer from design flaws that restrict their performance. To overcome these limitations, we proposed TIG-DETR (Texturized Instance Guidance DETR), a novel target detection model. TIG-DETR comprises a backbone network, TE-FPN (Texture-Enhanced FPN), and an enhanced DETR detector. TE-FPN addresses the issue of texture information loss in FPN by utilizing a bottom-up architecture, Lightweight Feature-wise Attention, and Feature-wise Attention. These components effectively compensate for texture information loss, mitigate the confounding effect of cross-scale fusion, and enhance the final output features. Additionally, we introduced the Instance Based Advanced Guidance Module in the DETR-based detector to tackle the weak detection of larger objects caused by the limitations of window interactions in Shifted Window-based Self-Attention. By incorporating TE-FPN instead of FPN in Faster RCNN and employing ResNet-50 as the backbone network, we observed an improvement of 1.9 AP in average accuracy. By introducing the Instance-Based Advanced Guidance Module, the average accuracy of the DETR-based target detector has been improved by 0.4 AP. TIG-DETR achieves an impressive average accuracy of 44.1% with ResNet-50 as the backbone network.

Bibliographic Details

Zhiyong Liu; Kehan Wang; Yixuan Wang; Guoqian Luo; Changming Li

MDPI AG

Materials Science; Physics and Astronomy; Engineering; Chemical Engineering; Computer Science

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know