arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.09730cs.CV
收藏

用于实时的目标检测的能量和GPU计算高效骨干网络

An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection

ETRI(韩国电子通信研究院);SK C&C

Youngwan Lee, Joong-won Hwang, Sangrok Lee, Yuseok Bae, Jongyoul Park

摘要:

由于DenseNet通过密集连接聚合具有不同感受野的中间特征,因此它在目标检测任务上表现出良好的性能。虽然特征重用使DenseNet能够用少量的模型参数和FLOP产生强大的特征,但DenseNet主干的检测器显示出相当慢的速度和低的能量效率。我们发现,线性增加的输入通道的密集连接导致沉重的内存访问成本,这将导致计算开销和更多的能量消耗。为了解决DenseNet的低效率,我们提出了一种称为VoVNet的能量和计算效率架构,该架构由单次聚合(OSA)组成。OSA不仅采用了DenseNet的多感受野表示多样化特征的优点,而且通过在最后一个特征图中仅聚合所有特征一次来克服密集连接的效率低下。为了验证VoVNet作为骨干网络的有效性,我们设计了轻量级和大型VoVNet,并将其应用于一级和两级对象检测器。我们基于VoVNet的检测器性能优于基于DenseNet的检测器,速度快2倍,能耗降低1.6 - 4.1倍。除了DenseNet之外,VoVNet还优于广泛使用的ResNet骨干网,具有更快的速度和更好的能源效率。特别是,小目标检测性能比DenseNet和ResNet有了显著提高。

英文摘要:

As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small number of model parameters and FLOPs, the detector with DenseNet backbone shows rather slow speed and low energy efficiency. We find the linearly increasing input channel by dense connection leads to heavy memory access cost, which causes computation overhead and more energy consumption. To solve the inefficiency of DenseNet, we propose an energy and computation efficient architecture called VoVNet comprised of One-Shot Aggregation (OSA). The OSA not only adopts the strength of DenseNet that represents diversified features with multi receptive fields but also overcomes the inefficiency of dense connection by aggregating all features only once in the last feature maps. To validate the effectiveness of VoVNet as a backbone network, we design both lightweight and large-scale VoVNet and apply them to one-stage and two-stage object detectors. Our VoVNet based detectors outperform DenseNet based ones with 2x faster speed and the energy consumptions are reduced by 1.6x - 4.1x. In addition to DenseNet, VoVNet also outperforms widely used ResNet backbone with faster speed and better energy efficiency. In particular, the small object detection performance has been significantly improved over DenseNet and ResNet.

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。

↑