Knowledge Commons of Institute of Automation,CAS
ScratchDet: Training Single-Shot Object Detectors from Scratch | |
Zhu, Rui1; Zhang, Shifeng2,3; Wang, Xiaobo1; Wen, Longyin1; Shi, Hailin1; Bo, Liefeng1; Mei, Tao1 | |
2019 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
会议日期 | 2019-06 |
会议地点 | 美国长滩 |
摘要 | Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional problems: 1) The classification and detection have different degrees of sensitivity to translation, resulting in the learning objective bias; 2) The architecture is limited by the classification network, leading to the inconvenience of modification. To cope with these problems, training detectors from scratch is a feasible solution. However, the detectors trained from scratch generally perform worse than the pretrained ones, even suffer from the convergence issue in training. In this paper, we explore to train object detectors from scratch robustly. By analysing the previous work on optimization landscape, we find that one of the overlooked points in current trained-from-scratch detector is the BatchNorm. Resorting to the stable and predictable gradient brought by BatchNorm, detectors can be trained from scratch stably while keeping the favourable performance independent to the network architecture. Taking this advantage, we are able to explore various types of networks for object detection, without suffering from the poor convergence. By extensive experiments and analyses on downsampling factor, we propose the Root-ResNet backbone network, which makes full use of the information from original images. Our ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39047 |
专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
作者单位 | 1.JD 2.Institute of Automation Chinese Academy of Sciences 3.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhu, Rui,Zhang, Shifeng,Wang, Xiaobo,et al. ScratchDet: Training Single-Shot Object Detectors from Scratch[C],2019. |
条目包含的文件 | 条目无相关文件。 |
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