.png){kind=icon}
返回
Feature-enhanced composite backbone network for object detection
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-024-18448-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the domain of object detection, the performance of a detector depend heavily on the quality of features extracted by the backbone network. Extraordinary feature representation has significantly improved the performance of the detector. As we all know, proposing a novel backbone structure requires meticulous structural design, a wealth of expert experience and tricks, and consumes a lot of computing resources. Therefore, it is meaningful to effectively leveraging the existing pre-trained backbones and maximize their performance to improve the accuracy of object detection. In this paper, we propose a novel Feature-enhanced Composite Backbone Network to improve the feature representation capability of the backbone, which called FECNet, equipped with Proportional Feature Fusion Module(PFF) and Multi-Granularity Information Aggregation and Interaction Method(MIAM). In particular, FECNet combines the existing backbones, which are connected by PFF, and FECNet pays more attention to extracting the discriminative features related to the object that are suitable for classification and the edge information suitable for bounding box regression through MIAM. Experiments show that FECNet is easily integrated into mainstream detectors and improve their performances. On the COCO 2017 dataset, employing ResNet50 as the foundational backbone, our approach attains a notable 3 percent increment in performance within the Fast R-CNN framework. Simultaneously, our method yields 2.1 percent enhancement when applied to the ResNet101 + Cascade R-CNN. And it's worth noting that applying our approach on the backbone swin transformer which is based on the trasformer structure gets an increase of more than 2 percent.
Keyword:
Feature-enhanced
Backbone
Representation
Object detection
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
分享收藏Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
PREAI
分享收藏A Continuous Cell Centrifuge for Lab Scale Perfusion Processes of Mammalian Cells一种用于实验室规模哺乳动物细胞灌注过程的连续细胞离心机
PREAI
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现.png)
Indoor Air
OAAI
Indoor AirIF0
OAAI分享收藏Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
PREAI
分享收藏
查看更多内容