The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
객체 감지는 컴퓨터 비전의 가장 중요한 측면 중 하나이며, 객체 감지에 CNN을 사용하면 다양한 분야에서 상당한 결과를 얻을 수 있습니다. 그러나 표준 컨볼루션 레이어의 고정 샘플링으로 인해 수용 필드가 고정된 위치로 제한되고 기하학적 변환에서 CNN이 제한됩니다. 이로 인해 얇은 객체 감지에 대한 CNN의 성능이 저하됩니다. 더 나은 가는 물체 감지 정확도와 효율성을 달성하기 위해 제안된 검출기 DFAM-DETR은 샘플링 포인트를 적응적으로 조정할 수 있을 뿐만 아니라 가는 물체의 특징에 초점을 맞추고 이미지의 전역에서 로컬로 필수 정보를 추출하는 기능을 향상시킵니다. 주의 메커니즘. 이 연구에서는 MS-COCO 데이터 세트의 얇은 개체 이미지를 사용합니다. 실험 결과는 DFAM-DETR이 CNN 및 변환기 기반 감지기에 비해 가는 물체에 대해 탁월한 감지 성능을 달성한다는 것을 보여줍니다.
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.
부
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
부
@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},}
부
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 -