.png){kind=icon}
返回
Incremental Embedding Learning With Disentangled Representation Translation
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3199816.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Humans are capable of accumulating knowledge by sequentially learning different tasks, while neural networks fail to achieve this due to catastrophic forgetting problems. Most current incremental learning methods focus more on tackling catastrophic forgetting for traditional classification networks. Notably, however, embedding networks that are basic architectures for many metric learning applications also suffer from this problem. Moreover, the most significant difficulty for continual embedding networks is that the relationships between the latent features and prototypes of previous tasks will be destroyed once new tasks have been learned. Accordingly, we propose a novel incremental method for embedding networks, called the disentangled representation translation (DRT) method, to obtain the discriminative class-disentangled features without reusing any samples of previous tasks and while avoiding the perturbation of task-related information. Next, a mask-guided module is specifically explored to adaptively change or retain the valuable information of latent features. This module enables us to effectively preserve the discriminative yet representative features in the disentangled translation process. In addition, DRT can easily be equipped with a regularization item of incremental learning to further improve performance. We conduct extensive experiments on four popular datasets; as the experimental results clearly demonstrate, our method can effectively alleviate the catastrophic forgetting problem for embedding networks.
Keyword:
Task analysis
Prototypes
Training
Semantics
Knowledge engineering
Perturbation methods
Adaptation models
Disentangled representation
embedding network
incremental learning
transfer learning
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Online Topology Learning by a Gaussian Membership-Based Self-Organizing Incremental Neural Network
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Plastic oscillators and fixed rhythms: Changes in the phase of clock-gene rhythms in the PVN are not reflected in the phase of the melatonin rhythm of grass rats.png)
Neuroscience
OAAI
NeuroscienceIF0
OAAI分享收藏Nitrogen Diffusion in Amorphous Silicon Nitride Isotope Multilayers Probed by Neutron ReflectometryOAAI
OAAI分享收藏
查看更多内容