A dynamic routing CapsNet based on increment prototype clustering for overcoming catastrophic forgetting
Abstract In continual learning, previously learnt knowledge tends to be overlapped by the subsequent training tasks. This bottleneck, known as catastrophic forgetting, has recently been relieved between vision tasks involving pixel shuffles etc. Nevertheless, the challenge lies in the continuous cla...
Main Authors: | Meng Wang, Zhengbing Guo, Huafeng Li |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2022-02-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/cvi2.12068 |
Similar Items
-
Emotion Recognition from Multiband EEG Signals Using CapsNet
by: Hao Chao, et al.
Published: (2019-05-01) -
Prediction of Peptide Detectability Based on CapsNet and Convolutional Block Attention Module
by: Minzhe Yu, et al.
Published: (2021-11-01) -
Classification of crop disease-pest questions based on BERT-BiGRU-CapsNet with attention pooling
by: Ting Zhang, et al.
Published: (2023-12-01) -
DE-CapsNet: A Diverse Enhanced Capsule Network with Disperse Dynamic Routing
by: Bohan Jia, et al.
Published: (2020-01-01) -
SD-CapsNet: A Siamese Dense Capsule Network for SAR Image Registration with Complex Scenes
by: Bangjie Li, et al.
Published: (2023-03-01)