Improving SVM accuracy by training on auxiliary data sources
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Object Class Recognition by Boosting a Part-Based Model
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Constructing informative priors using transfer learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
Learning Parts-Based Representations of Data
The Journal of Machine Learning Research
Boosting for transfer learning
Proceedings of the 24th international conference on Machine learning
Self-taught learning: transfer learning from unlabeled data
Proceedings of the 24th international conference on Machine learning
A Multitask Learning Approach to Face Recognition Based on Neural Networks
IDEAL '08 Proceedings of the 9th International Conference on Intelligent Data Engineering and Automated Learning
Deep transfer via second-order Markov logic
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Hierarchical Multi-view Fisher Discriminant Analysis
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Creating an ensemble of diverse support vector machines using adaboost
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Transfer learning, serving as one of the most popular theory in machine learning, has attracted a lot of attention recently. In this paper, we propose a new learning strategy called part-based transfer learning (pbTL), which is a process of parameter transfer. Dissimilar to many traditional works, we consider how to transfer the information from one task to another in the form of parts. We regard all the complex tasks as a collection of constituent parts and every task can be divided into several parts respectively. It means transfer learning between two complex tasks can be accomplished by sub-transfer learning tasks between their parts. Through developing it in this hierarchical fasion, we can reach a better outcome. Experiments on synthetic data with support vector machines (SVMs) validate the effectiveness of the proposed learning framework.