DFAM-DETR: Deformable feature based attention mechanism DETR on slender object detection

TL;DR

This paper introduces DFAM-DETR, an improved deformable transformer-based object detector that enhances slender object detection accuracy and efficiency by integrating deformable convolution and attention mechanisms.

Contribution

It proposes the DFAM module to augment Deformable DETR, significantly improving slender object detection performance over existing methods.

Findings

Achieves superior detection accuracy on slender objects.

Outperforms existing CNN-based and transformer-based detectors.

Enhances detection efficiency with adaptive sampling points.

Abstract

Object detection is one of the most significant aspects of computer vision, and it has achieved substantial results in a variety of domains. It is worth noting that there are few studies focusing on slender object detection. CNNs are widely employed in object detection, however it performs poorly on slender object detection due to the fixed geometric structure and sampling points. In comparison, Deformable DETR has the ability to obtain global to specific features. Even though it outperforms the CNNs in slender objects detection accuracy and efficiency, the results are still not satisfactory. Therefore, we propose Deformable Feature based Attention Mechanism (DFAM) to increase the slender object detection accuracy and efficiency of Deformable DETR. The DFAM has adaptive sampling points of deformable convolution and attention mechanism that aggregate information from the entire input sequence in the backbone network. This improved detector is named as Deformable Feature based Attention Mechanism DETR (DFAM- DETR). Results indicate that DFAM-DETR achieves outstanding detection performance on slender objects.