arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.10959cs.CVcs.LG
收藏

使用嫁接网络学习利用多种视觉模式

Learning to Exploit Multiple Vision Modalities by Using Grafted Networks

Institute of Neuroinformatics, University of Zürich and ETH Zürich(苏黎世大学与苏黎世联邦理工学院神经信息学研究所)

Yuhuang Hu, Tobi Delbruck, Shih-Chii Liu

摘要:

诸如热、高光谱、偏振和事件相机等新型视觉传感器提供了传统强度相机无法提供的信息。将这些传感器与当前强大的深度神经网络一起使用的一个障碍是缺乏大型标记训练数据集。本文提出了一种网络移植算法(NGA),其中由非常规视觉输入驱动的新前端网络取代了处理强度帧的预训练深度网络的前端网络。自监督训练仅使用同步记录的强度帧和新的传感器数据,以最大限度地提高预训练网络和嫁接网络之间的特征相似性。我们表明,增强的嫁接网络达到竞争力的平均精度(AP 50)分数的预训练网络上的目标检测任务使用热和事件相机数据集,而没有增加推理成本。特别地,由热框架驱动的接枝网络显示出比使用强度框架相对提高49.11%。移植的前端仅具有总参数的5- 8%,并且可以在几个小时内在单个GPU上训练,相当于从标记数据训练整个对象检测器所需时间的5%。NGA允许新的视觉传感器利用以前预先训练的强大的深度模型,节省训练成本,并扩大新型传感器的应用范围。

英文摘要:

Novel vision sensors such as thermal, hyperspectral, polarization, and event cameras provide information that is not available from conventional intensity cameras. An obstacle to using these sensors with current powerful deep neural networks is the lack of large labeled training datasets. This paper proposes a Network Grafting Algorithm (NGA), where a new front end network driven by unconventional visual inputs replaces the front end network of a pretrained deep network that processes intensity frames. The self-supervised training uses only synchronously-recorded intensity frames and novel sensor data to maximize feature similarity between the pretrained network and the grafted network. We show that the enhanced grafted network reaches competitive average precision (AP50) scores to the pretrained network on an object detection task using thermal and event camera datasets, with no increase in inference costs. Particularly, the grafted network driven by thermal frames showed a relative improvement of 49.11% over the use of intensity frames. The grafted front end has only 5--8% of the total parameters and can be trained in a few hours on a single GPU equivalent to 5% of the time that would be needed to train the entire object detector from labeled data. NGA allows new vision sensors to capitalize on previously pretrained powerful deep models, saving on training cost and widening a range of applications for novel sensors.

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。

↑