计算机科学
目标检测
比例(比率)
人工智能
构造(python库)
对象(语法)
转化(遗传学)
三叉戟
特征(语言学)
采样(信号处理)
探测器
计算机视觉
方案(数学)
模式识别(心理学)
数学
地理
哲学
考古
化学
程序设计语言
数学分析
基因
电信
地图学
生物化学
语言学
作者
Yanghao Li,Yuntao Chen,Naiyan Wang,Zhaoxiang Zhang
出处
期刊:
日期:2019-10-01
卷期号:: 6053-6062
被引量:1056
标识
DOI:10.1109/iccv.2019.00615
摘要
Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.
科研通智能强力驱动
Strongly Powered by AbleSci AI