arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.02293cs.CV
收藏

用于目标检测的高效神经结构搜索级变换

Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection

University of Chinese Academy of Sciences(中国科学院大学);SenseTime Group Limited(商汤集团有限公司);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)

Junran Peng, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, Junjie Yan

摘要:

近年来,神经结构搜索在大规模图像分类中取得了巨大的成功。相比之下,专注于目标检测的架构搜索的工作有限,主要是因为检测器总是需要昂贵的ImageNet预训练。从头开始训练,作为一种替代,需要更多的时代收敛,并没有带来计算节省。为了克服这一障碍,本文提出了一种实用的神经结构变换搜索(NATS)算法用于目标检测。NATS不需要搜索和构造整个网络,而是在现有网络的基础上探索体系结构空间,重用其权值。我们提出了一种新的神经网络结构的搜索策略,在通道级而不是路径级,并设计了一个专门针对目标检测的搜索空间。通过这两种设计的结合,可以发现一种架构转换方案,以使设计用于图像分类的网络适应目标检测任务。由于我们的方法是基于梯度的,并且只搜索一个变换方案,因此在ImageNet中预训练的模型的权重可以在搜索和再训练阶段都被利用,这使得整个过程非常高效。变换后的网络不需要额外的参数和浮点数,易于硬件优化,在实时应用中具有实用价值。在实验中,我们证明了NATSon网络的有效性,如ResNet和ResNeXt。我们改造后的网络与各种检测框架相结合,在保持快速的同时,对COCO数据集进行了重大改进。

英文摘要:

Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for object detection, mainly because the costly ImageNet pre-training is always required for detectors. Training from scratch, as a substitute, demands more epochs to converge and brings no computation saving. To overcome this obstacle, we introduce a practical neural architecture transformation search(NATS)algorithm for object detection in this paper. Instead of searching and constructing an entire network, NATS explores the architecture space on the base of existing network and reusing its weights. We propose a novel neural architecture search strategy in channel-level instead of path-level and devise a search space specially targeting at object detection. With the combination of these two designs, an architecture transformation scheme could be discovered to adapt a network designed for image classification to task of object detection. Since our method is gradient-based and only searches for a transformation scheme, the weights of models pretrained inImageNet could be utilized in both searching and retraining stage, which makes the whole process very efficient. The transformed network requires no extra parameters and FLOPs, and is friendly to hardware optimization, which is practical to use in real-time application. In experiments, we demonstrate the effectiveness of NATSon networks like ResNet and ResNeXt. Our transformed networks, combined with various detection frameworks, achieve significant improvements on the COCO dataset while keeping fast.

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。

↑