Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection | |
Peng, Junran1,2,3; Sun, Ming2; Zhang, Zhaoxiang1,3; Tan, Tieniu1,3; Yan, Junjie2 | |
2019 | |
会议名称 | Advances in Neural Information Processing Systems |
会议日期 | 2019 |
会议地点 | 加拿大 |
摘要 | Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on archi- tecture search for object detection, mainly because the costly ImageNet pretraining 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 archi- tecture 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 in ImageNet 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 NATS on networks like ResNet and ResNeXt. Our transformed networks, combined with various detection frameworks, achieve significant improvements on the COCO dataset while keeping fast. |
关键词 | Object detection AutoML NAS |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42203 |
专题 | 模式识别实验室 |
通讯作者 | Zhang, Zhaoxiang |
作者单位 | 1.University of Chinese Academy of Sciences 2.SenseTime Group Limited 3.Center for Research on Intelligent Perception and Computing, CASIA |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Peng, Junran,Sun, Ming,Zhang, Zhaoxiang,et al. Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
pjr_NIPS_NATS.pdf(2068KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论