• Home
  • Search
  • Sparse Deep Transfer Learning for Convolutional Neural Network
  • Cite Icon51
  • https://doi.org/10.1609/aaai.v31i1.10801Copy DOI Icon

Sparse Deep Transfer Learning for Convolutional Neural Network

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Extensive studies have demonstrated that the representations of convolutional neural networks (CNN), which are learned from a large-scale data set in the source domain, can be effectively transferred to a new target domain. However, compared to the source domain, the target domain often has limited data in practice. In this case, overfitting may significantly depress transferability, due to the model redundancy of the intensive CNN structures. To deal with this difficulty, we propose a novel sparse deep transfer learning approach for CNN. There are three main contributions in this work. First, we introduce a Sparse-SourceNet to reduce the redundancy in the source domain. Second, we introduce a Hybrid-TransferNet to improve the generalization ability and the prediction accuracy of transfer learning, by taking advantage of both model sparsity and implicit knowledge. Third, we introduce a Sparse-TargetNet, where we prune our Hybrid-TransferNet to obtain a highly-compact, source-knowledge-integrated CNN in the target domain. To examine the effectiveness of our methods, we perform our sparse deep transfer learning approach on a number of benchmark transfer learning tasks. The results show that, compared to the standard fine-tuning approach, our proposed approach achieves a significant pruning rate on CNN while improves the accuracy of transfer learning.

Similar Papers
  • PDF
  • Research Article
  • Citations43

Multi-Source Deep Transfer Neural Network Algorithm

  • Sep 16, 2019
  • Sensors (Basel, Switzerland)
  • Jingmei Li +3
  • Research Article
  • Citations59

Transfer Learning for Deep Learning on Graph-Structured Data

  • Feb 13, 2017
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Jaekoo Lee +3
  • Book Chapter
  • Citations1

Stepwise Transfer of Domain Knowledge for Computer-Aided Diagnosis in Pathology Using Deep Neural Networks

  • Jan 01, 2020
  • Jia Qu +5
  • PDF
  • Research Article
  • Citations7

Deep Transfer Learning for Biology Cross-Domain Image Classification

  • Dec 15, 2021
  • Journal of Control Science and Engineering
  • Chunfeng Guo +2
  • Research Article
  • Citations17

A deep transfer learning approach for Real-Time traffic conflict prediction with trajectory data.

  • May 01, 2025
  • Accident; analysis and prevention
  • Qinzhong Hou +4
  • Conference Article
  • Citations43

Deep Transfer Learning for Single-Channel Automatic Sleep Staging with Channel Mismatch

  • Sep 01, 2019
  • Huy Phan +4
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations5

The Role of Knowledge Creation-Oriented Convolutional Neural Network in Learning Interaction.

  • Mar 16, 2022
  • Computational Intelligence and Neuroscience
  • Hongyan Zhang +1
  • Research Article
  • Citations267

Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis with unlabeled or insufficient labeled data

  • May 26, 2020
  • Neurocomputing
  • Cheng Cheng +4
  • PDF
  • Research Article
  • Citations120

Convolutional Neural Network Coupled with a Transfer-Learning Approach for Time-Series Flood Predictions

  • Dec 26, 2019
  • Water
  • Nobuaki Kimura +4
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Research Article
  • Citations42

Intelligent diagnosis method for machine faults based on federated transfer learning

  • Jun 28, 2024
  • Applied Soft Computing
  • Zhinong Li +2
  • Research Article
  • Citations10

Domain-Specific Dual Network With Unsupervised Domain Adaptation for Transfer Fault Prognosis Across Machines Using Multiple Source Domains

  • Jan 01, 2025
  • IEEE Transactions on Instrumentation and Measurement
  • Smaran Khanal +5
  • Research Article
  • Citations263

A New Deep Transfer Learning Method for Bearing Fault Diagnosis Under Different Working Conditions

  • Aug 01, 2020
  • IEEE Sensors Journal
  • Jun Zhu +2
  • Research Article
  • Citations64

Domain- and task-specific transfer learning for medical segmentation tasks

  • Nov 23, 2021
  • Computer Methods and Programs in Biomedicine
  • Riaan Zoetmulder +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.