Knowledge Commons of Institute of Automation,CAS
DeepCollaboration: Collaborative Generative and Discriminative Models for Class Incremental Learning | |
Cui B(崔波)1,2![]() ![]() ![]() | |
2021-05 | |
会议名称 | AAAI Conference on Artificial Intelligence |
会议日期 | 2021 |
会议地点 | ELECTR NETWORK |
摘要 | An important challenge for neural networks is to learn incrementally, i.e., learn new classes without catastrophic forgetting. To overcome this problem, generative replay technique has been suggested, which can generate samples belonging to learned classes while learning new ones. However, such generative models usually suffer from increased distribution mismatch between the generated and original samples along the learning process. In this work, we propose DeepCollaboration (D-Collab), a collaborative framework of deep generative and discriminative models to solve this problem effectively. We develop a discriminative learning model to incrementally update the latent feature space for continual classification. At the same time, a generative model is introduced to achieve conditional generation using the latent feature distribution produced by the discriminative model. Importantly, the generative and discriminative models are connected through bidirectional training to enforce cycle-consistency of mappings between feature and image domains. Furthermore, a domain alignment module is used to eliminate the divergence between the feature distributions of generated images and real ones. This module together with the discriminative model can perform effective sample mining to facilitate incremental learning. Extensive experiments on several visual recognition datasets show that our system can achieve state-of-the-art performance. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 类脑模型与计算 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44719 |
专题 | 脑图谱与类脑智能实验室_脑网络组研究 |
通讯作者 | Yu S(余山) |
作者单位 | 1.Chinese Acad Sci CASIA, Natl Lab Pattern Recognit, Brainnetome Ctr, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R 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 B,Hu GY,Yu S. DeepCollaboration: Collaborative Generative and Discriminative Models for Class Incremental Learning[C],2021. |
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 | ||
16204-Article Text-1(4923KB) | 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