Object detection is one of the most important aspects of computer vision, and the use of CNNs for object detection has yielded substantial results in a variety of fields. However, due to the fixed sampling in standard convolution layers, it restricts receptive fields to fixed locations and limits CNNs in geometric transformations. This leads to poor performance of CNNs for slender object detection. In order to achieve better slender object detection accuracy and efficiency, this proposed detector DFAM-DETR not only can adjust the sampling points adaptively, but also enhance the ability to focus on slender object features and extract essential information from global to local on the image through an attention mechanism. This study uses slender objects images from MS-COCO dataset. The experimental results show that DFAM-DETR achieves excellent detection performance on slender objects compared to CNN and transformer-based detectors.
Feng WEN
Shenyang Ligong University
Mei WANG
Shenyang Ligong University
Xiaojie HU
Shenyang Ligong University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Feng WEN, Mei WANG, Xiaojie HU, "DFAM-DETR: Deformable Feature Based Attention Mechanism DETR on Slender Object Detection" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 3, pp. 401-409, March 2023, doi: 10.1587/transinf.2022EDP7111.
Abstract: Object detection is one of the most important aspects of computer vision, and the use of CNNs for object detection has yielded substantial results in a variety of fields. However, due to the fixed sampling in standard convolution layers, it restricts receptive fields to fixed locations and limits CNNs in geometric transformations. This leads to poor performance of CNNs for slender object detection. In order to achieve better slender object detection accuracy and efficiency, this proposed detector DFAM-DETR not only can adjust the sampling points adaptively, but also enhance the ability to focus on slender object features and extract essential information from global to local on the image through an attention mechanism. This study uses slender objects images from MS-COCO dataset. The experimental results show that DFAM-DETR achieves excellent detection performance on slender objects compared to CNN and transformer-based detectors.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7111/_p
Copy
@ARTICLE{e106-d_3_401,
author={Feng WEN, Mei WANG, Xiaojie HU, },
journal={IEICE TRANSACTIONS on Information},
title={DFAM-DETR: Deformable Feature Based Attention Mechanism DETR on Slender Object Detection},
year={2023},
volume={E106-D},
number={3},
pages={401-409},
abstract={Object detection is one of the most important aspects of computer vision, and the use of CNNs for object detection has yielded substantial results in a variety of fields. However, due to the fixed sampling in standard convolution layers, it restricts receptive fields to fixed locations and limits CNNs in geometric transformations. This leads to poor performance of CNNs for slender object detection. In order to achieve better slender object detection accuracy and efficiency, this proposed detector DFAM-DETR not only can adjust the sampling points adaptively, but also enhance the ability to focus on slender object features and extract essential information from global to local on the image through an attention mechanism. This study uses slender objects images from MS-COCO dataset. The experimental results show that DFAM-DETR achieves excellent detection performance on slender objects compared to CNN and transformer-based detectors.},
keywords={},
doi={10.1587/transinf.2022EDP7111},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - DFAM-DETR: Deformable Feature Based Attention Mechanism DETR on Slender Object Detection
T2 - IEICE TRANSACTIONS on Information
SP - 401
EP - 409
AU - Feng WEN
AU - Mei WANG
AU - Xiaojie HU
PY - 2023
DO - 10.1587/transinf.2022EDP7111
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2023
AB - Object detection is one of the most important aspects of computer vision, and the use of CNNs for object detection has yielded substantial results in a variety of fields. However, due to the fixed sampling in standard convolution layers, it restricts receptive fields to fixed locations and limits CNNs in geometric transformations. This leads to poor performance of CNNs for slender object detection. In order to achieve better slender object detection accuracy and efficiency, this proposed detector DFAM-DETR not only can adjust the sampling points adaptively, but also enhance the ability to focus on slender object features and extract essential information from global to local on the image through an attention mechanism. This study uses slender objects images from MS-COCO dataset. The experimental results show that DFAM-DETR achieves excellent detection performance on slender objects compared to CNN and transformer-based detectors.
ER -