A Sub-Model Detachable Convolutional Neural Network
- https://doi.org/10.2991/jrnal.k.210521.012How to use a DOI?
- Convolutional neural networks, supervised learning, model compression
In this research, we propose a Convolutional Network with sub-Networks (CNSN), i.e., a Convolutional Neural Network (CNN) or base-model that can be divided into sub-models on demand. The CNN architecture, entails that feature map shapes are varied throughout the model, therefore, the hidden layer within CNN may not directly process an input image without modification. To address this problem, we propose a step-down convolutional layer, which is a convolutional layer acting as an input layer for the sub-model. This step-down convolutional layer reshapes and processes an input image to a preferred representation to the sub-model. To train CNSN, we treat the base-model and sub-models as distinct models. Each model is forward- and back-propagated separately. Using multi-model loss, i.e., a linear combination of losses from base-model and sub-models, we thus update model parameters that can be utilized in both base-model and sub-models.
- © 2021 The Authors. Published by Atlantis Press B.V.
- Open Access
- This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - JOUR AU - Ninnart Fuengfusin AU - Hakaru Tamukoh PY - 2021 DA - 2021/05 TI - A Sub-Model Detachable Convolutional Neural Network JO - Journal of Robotics, Networking and Artificial Life SN - 2352-6386 UR - https://doi.org/10.2991/jrnal.k.210521.012 DO - https://doi.org/10.2991/jrnal.k.210521.012 ID - Fuengfusin2021 ER -