arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.01892cs.CV
收藏

基于尺度感知的Trident网络的目标检测

Scale-Aware Trident Networks for Object Detection

University of Chinese Academy of Sciences(中国科学院大学);Center for Research on Intelligent Perception and Computing, CASIA(中国科学院自动化研究所智能感知与计算研究中心);TuSimple(图森未来);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心)

Yanghao Li, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang

摘要:

尺度变化是目标检测中的关键问题之一。在这项工作中,我们首先提出了一个控制实验,以探讨感受野的影响,规模变化的目标检测。基于探索实验的结果,我们提出了一种新的三叉神经网络(TridentNet),旨在生成具有统一表示能力的特定尺度特征图。我们构建了一个并行的多分支架构,其中每个分支共享相同的转换参数,但具有不同的感受野。然后,我们采用了一个规模感知的训练计划,专门每个分支的采样对象实例的适当规模的训练。作为奖励,与香草检测器相比,TridentNet的快速近似版本可以在没有任何额外参数和计算成本的情况下实现显着改进。在COCO数据集上,我们使用ResNet-101主干的TridentNet实现了48.4 mAP的最先进的单模型结果。代码可在https://git.io/fj5vR上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑