Knowledge Commons of Institute of Automation,CAS
Balanced Ranking and Sorting for Class Incremental Object Detection | |
Cui, Bo1,2![]() ![]() ![]() | |
2022 | |
会议名称 | IEEE International Conference on Acoustics, Speech and Signal Processing |
会议日期 | 2022-5 |
会议地点 | ELECTR NETWORK |
出版者 | IEEE |
摘要 | Class incremental learning has drawn much attention recently. Although many algorithms have been proposed for class incremental image classification, developing object detectors which can learn incrementally is still a challenge. Existing methods rely on knowledge distillation to achieve class incremental object detection (CIOD), which suffer from performance tradeoff between old and new classes. In this paper, we propose balanced ranking and sorting (BRS), to tackle the catastrophic forgetting and data imbalance problems for CIOD. Specifically, ranking \& sorting with pseudo ground truths (RSP) and ranking \& sorting transfer (RST) are developed to preserve the learned knowledge from the old model while learning new classes, in an unified framework. To mitigate the data imbalance problem, gradient rebalancing is performed with specific sample pairs. We demonstrate the effectiveness of our approach with extensive experiments on PASCAL VOC and COCO datasets, in which significant improvement over state-of-the-art methods is achieved. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48632 |
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 NLPR, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.School of Future Technology, University of Chinese Academy of Sciences 4.CAS Center for Excellence in Brain Science and Intelligence Technology 5.X-Lab, the Second Academy of CASIC, Beijing, 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,Qu, Hui,Huang, Xuhui,et al. Balanced Ranking and Sorting for Class Incremental Object Detection[C]:IEEE,2022. |
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 | ||
ICASSP_2022_CB.pdf(3679KB) | 会议论文 | 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