Sparse Deep Transfer Learning for Convolutional Neural Network | |
Jiaming Liu; Yali Wang; Yu Qiao | |
2017 | |
会议地点 | San Francisco, California USA |
英文摘要 | 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 highlycompact, 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. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/11758] |
专题 | 深圳先进技术研究院_集成所 |
作者单位 | 2017 |
推荐引用方式 GB/T 7714 | Jiaming Liu,Yali Wang,Yu Qiao. Sparse Deep Transfer Learning for Convolutional Neural Network[C]. 见:. San Francisco, California USA. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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