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
1단계 객체 검출 방법에 대해 입력 영상의 수평 이동이 미치는 영향을 조사했습니다. 우리는 대상 물체 중심이 격자 경계에 있을 때 물체 탐지기 클래스 점수가 떨어지는 것을 발견했습니다. 많은 접근법은 시프트 불변성을 달성하기 위해 다운샘플링의 앨리어싱 효과를 줄이는 데 중점을 두었습니다. 그러나 다운샘플링은 그리드 경계에서 이 문제를 완전히 해결하지 못합니다. 그리드 경계에 가까운 픽셀의 특징이 인접한 그리드 셀로 분산되는 것을 억제하는 것이 필요합니다. 따라서 본 논문에서는 현재 객체 검출 방법의 이러한 약점을 개선하기 위해 그리드 경계에 초점을 맞춘 두 가지 접근 방식을 제안한다. 하나는 분류 헤드의 입력에 하위 그리드 기능이 추가되는 하위 그리드 기능 추출 모듈입니다. 다른 하나는 그리드 수준 변화에 의해 증강된 데이터가 생성되어 훈련에 사용되는 그리드 인식 데이터 증강(Grid-Aware Data Augmentation)입니다. 제안된 방법의 효율성은 제안된 방법을 FCOS 아키텍처에 적용한 후 COCO 검증 세트를 사용하여 입증됩니다.
Shinji UCHINOURA
from Hiroshima University
Takio KURITA
from Hiroshima 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
Shinji UCHINOURA, Takio KURITA, "Improved Head and Data Augmentation to Reduce Artifacts at Grid Boundaries in Object Detection" in IEICE TRANSACTIONS on Information,
vol. E107-D, no. 1, pp. 115-124, January 2024, doi: 10.1587/transinf.2023EDP7079.
Abstract: We investigated the influence of horizontal shifts of the input images for one stage object detection method. We found that the object detector class scores drop when the target object center is at the grid boundary. Many approaches have focused on reducing the aliasing effect of down-sampling to achieve shift-invariance. However, down-sampling does not completely solve this problem at the grid boundary; it is necessary to suppress the dispersion of features in pixels close to the grid boundary into adjacent grid cells. Therefore, this paper proposes two approaches focused on the grid boundary to improve this weak point of current object detection methods. One is the Sub-Grid Feature Extraction Module, in which the sub-grid features are added to the input of the classification head. The other is Grid-Aware Data Augmentation, where augmented data are generated by the grid-level shifts and are used in training. The effectiveness of the proposed approaches is demonstrated using the COCO validation set after applying the proposed method to the FCOS architecture.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7079/_p
부
@ARTICLE{e107-d_1_115,
author={Shinji UCHINOURA, Takio KURITA, },
journal={IEICE TRANSACTIONS on Information},
title={Improved Head and Data Augmentation to Reduce Artifacts at Grid Boundaries in Object Detection},
year={2024},
volume={E107-D},
number={1},
pages={115-124},
abstract={We investigated the influence of horizontal shifts of the input images for one stage object detection method. We found that the object detector class scores drop when the target object center is at the grid boundary. Many approaches have focused on reducing the aliasing effect of down-sampling to achieve shift-invariance. However, down-sampling does not completely solve this problem at the grid boundary; it is necessary to suppress the dispersion of features in pixels close to the grid boundary into adjacent grid cells. Therefore, this paper proposes two approaches focused on the grid boundary to improve this weak point of current object detection methods. One is the Sub-Grid Feature Extraction Module, in which the sub-grid features are added to the input of the classification head. The other is Grid-Aware Data Augmentation, where augmented data are generated by the grid-level shifts and are used in training. The effectiveness of the proposed approaches is demonstrated using the COCO validation set after applying the proposed method to the FCOS architecture.},
keywords={},
doi={10.1587/transinf.2023EDP7079},
ISSN={1745-1361},
month={January},}
부
TY - JOUR
TI - Improved Head and Data Augmentation to Reduce Artifacts at Grid Boundaries in Object Detection
T2 - IEICE TRANSACTIONS on Information
SP - 115
EP - 124
AU - Shinji UCHINOURA
AU - Takio KURITA
PY - 2024
DO - 10.1587/transinf.2023EDP7079
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E107-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2024
AB - We investigated the influence of horizontal shifts of the input images for one stage object detection method. We found that the object detector class scores drop when the target object center is at the grid boundary. Many approaches have focused on reducing the aliasing effect of down-sampling to achieve shift-invariance. However, down-sampling does not completely solve this problem at the grid boundary; it is necessary to suppress the dispersion of features in pixels close to the grid boundary into adjacent grid cells. Therefore, this paper proposes two approaches focused on the grid boundary to improve this weak point of current object detection methods. One is the Sub-Grid Feature Extraction Module, in which the sub-grid features are added to the input of the classification head. The other is Grid-Aware Data Augmentation, where augmented data are generated by the grid-level shifts and are used in training. The effectiveness of the proposed approaches is demonstrated using the COCO validation set after applying the proposed method to the FCOS architecture.
ER -