I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting
文献类型：会议论文
| 作者 | Dong JH(董家华)2,3,4 ; Cong Y(丛杨)2,3; Sun G(孙干)2,3; Ma BT(马兵涛)2,3,4; Wang LC(王莅尘)1
|
| 出版日期 | 2021 |
| 会议日期 | Febuary 2-9, 2021 |
| 会议地点 | ELECTR NETWORK |
| 页码 | 6066-6074 |
| 英文摘要 | 3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of past 3D object classes when facing the common real-world scenario: new classes of 3D objects arrive in a sequence. Moreover, the performance of advanced approaches degrades dramatically for past learned classes (i.e., catastrophic forgetting), due to the irregular and redundant geometric structures of 3D point cloud data. To address these challenges, we propose a new Incremental 3D Object Learning (i.e., I3DOL) model, which is the first exploration to learn new classes of 3D object continually. Specifically, an adaptive-geometric centroid module is designed to construct discriminative local geometric structures, which can better characterize the irregular point cloud representation for 3D object. Afterwards, to prevent the catastrophic forgetting brought by redundant geometric information, a geometric-aware attention mechanism is developed to quantify the contributions of local geometric structures, and explore unique 3D geometric characteristics with high contributions for classes incremental learning. Meanwhile, a score fairness compensation strategy is proposed to further alleviate the catastrophic forgetting caused by unbalanced data between past and new classes of 3D object, by compensating biased prediction for new classes in the validation phase. Experiments on 3D representative datasets validate the superiority of our I3DOL framework. |
| 源文献作者 | Association for the Advancement of Artificial Intelligence |
| 产权排序 | 1 |
| 会议录 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
 |
| 会议录出版者 | AAAI |
| 会议录出版地 | Palo Alto, California |
| 语种 | 英语 |
| ISSN号 | 2159-5399 |
| ISBN号 | 978-1-57735-866-4 |
| WOS记录号 | WOS:000680423506020 |
| 源URL | [http://ir.sia.cn/handle/173321/29553]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Cong Y(丛杨) |
| 作者单位 | 1.Northeastern University, Boston, USA 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016, China 4.University of Chinese Academy of Sciences, Beijing, 100049, China |
| 推荐引用方式 GB/T 7714 | Dong JH,Cong Y,Sun G,et al. I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting[C]. 见:. ELECTR NETWORK. Febuary 2-9, 2021. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
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。