特征(语言学)
探测器
单发
光学(聚焦)
模式识别(心理学)
人工智能
计算机科学
弹丸
计算机视觉
物理
光学
电信
哲学
语言学
化学
有机化学
作者
Xianlin Dong,Feng Li,Huihui Bai,Yao Zhao
出处
期刊:Smart innovation, systems and technologies
日期:2022-01-01
卷期号:: 191-201
标识
DOI:10.1007/978-981-19-1057-9_19
摘要
Dong, Xiang Li, Feng Bai, Huihui Zhao, YaoConsidering the impact of the balance between real-time performance and detection accuracy, single-stage detectors have received more attention than two-stage detectors. However, due to a large number of detection objects with different sizes, the existing detectors still have limitations in terms of scale variations. To improve the situation, we propose a feature-aware network based on upper triangular interaction (UTINet), which introduces an upper triangular interaction module (UTIM) to focus on features of different scales and progressively interact with each other. Moreover, we build a feature-aware enhancement module (FAEM) to learn more comprehensive feature representations by amplifying the feature differences before and after fusion. Experiments are performed on MS COCO, and our UTINet with a $$300 \times 300$$ input achieves superior performance of 33.3% mAP compared with existing methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI