Knowledge Commons of Institute of Automation,CAS
RT-Net: Replay-and-Transfer Network for Class Incremental Object Detection | |
Cui, Bo1,2; Hu, Guyue1,2; Yu, Shan1,3,4 | |
发表期刊 | Applied Intelligence |
2022 | |
页码 | 0 |
摘要 | Despite the remarkable performance achieved by DNN-based object detectors, class incremental object detection (CIOD) remains a challenge, in which the network has to learn to detect novel classes sequentially. Catastrophic forgetting is the main problem underlying this difficulty, as neural networks tend to detect new classes only when training samples for old classes are absent. In this paper, we propose the Replay-and-Transfer Network (RT-Net) to address this issue and accomplish CIOD. We develop a generative replay model to replay features of old classes during learning of new ones for the RoI (Region of Interest) head, using the stored latent feature distributions. To overcome the drastic changes of the RoI feature space, guided feature distillation and feature translation are introduced to facilitate knowledge transfer from the old model to the new one. In addition, we propose holistic ranking transfer, which transfers ranking orders of proposals to the new model, to enable the region proposal network to identify high quality proposals for old classes. Importantly, this framework provides a general solution for CIOD, which can be successfully applied to two task settings: set-overlapped, in which the old and new training sets are overlapped, and set-disjoint, in which the old and new tasks have unique samples. Extensive experiments on standard benchmark datasets including PASCAL VOC and COCO show that RT-Net can achieve state-of-the-art performance for CIOD. |
收录类别 | SCI |
WOS记录号 | WOS:000835607800010 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48631 |
专题 | 脑图谱与类脑智能实验室_脑网络组研究 |
通讯作者 | Cui, Bo |
作者单位 | 1.Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China 3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing 100190, China 4.School of Future Technology, University of Chinese Academy of Sciences, Beijing 100049, China |
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 | Cui, Bo,Hu, Guyue,Yu, Shan. RT-Net: Replay-and-Transfer Network for Class Incremental Object Detection[J]. Applied Intelligence,2022:0. |
APA | Cui, Bo,Hu, Guyue,&Yu, Shan.(2022).RT-Net: Replay-and-Transfer Network for Class Incremental Object Detection.Applied Intelligence,0. |
MLA | Cui, Bo,et al."RT-Net: Replay-and-Transfer Network for Class Incremental Object Detection".Applied Intelligence (2022):0. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
revised.pdf(12588KB) | 期刊论文 | 作者接受稿 | 暂不开放 | CC BY-NC-SA |
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