.png){kind=icon}
返回
AugFCOS: Augmented fully convolutional one-stage object detection network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.109098.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As a pioneering work of introducing the idea of full convolutional network into the field of object detection, the fully convolutional one-stage object detection network (FCOS) has the advantage of excellent performance with low memory overhead. However, there are certain problems with FCOS that merit more research: the centerness quality assessment loss does not decrease during the late training stage, and its adaptive training sample selection (ATSS) relies heavily on the hyperparameter. To solve the aforementioned problems, we propose a novel object detection network, named augmented fully convolutional one-stage object detection network (AugFCOS). First of all, we propose an improved dynamic optimization loss (DOL) to mitigate the impact of the original centerness loss not decreasing. Then, a Robust Training Sample Selection (RTSS) is proposed to get rid of the dependence of hyper-parameter in ATSS of FCOS. Finally, a novel mixed attention feature pyramid network (MAFPN) is presented to enhance the multi-scale representation ability of feature pyramid network (FPN) and further improve the ability of multi-scale detection. The experimental results on MS COCO demonstrate the effectiveness of our proposed AugFCOS, where AugFCOS achieves approximate 2.0% to 2.9% increase when compared with ATSS and FCOS. (c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Feature pyramid network
Object detection
Sample selection
Attention module
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Multiple attentional pyramid networks for Chinese herbal recognition用于中药识别的多注意金字塔网络.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression propertiesRSC Advances
RSC AdvancesIF0
PREAI
分享收藏Adaptive region-aware feature enhancement for object detection用于目标检测的自适应区域感知特征增强PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏SA-DPNet: Structure-aware dual pyramid network for salient object detectionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏mSODANet: A network for multi-scale object detection in aerial images using hierarchical dilated convolutions *PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏X-ray investigation of the coordination and complex formation of lanthanoid ions in aqueous perchlorate and selenate solutions高氯酸盐和硒酸水溶液中镧系离子的配位和络合物形成的x射线研究
PREAI
分享收藏 没有更多内容
没有更多内容