Coupled End-to-End Transfer Learning with Generalized Fisher Information
Coupled End-to-End Transfer Learning with Generalized Fisher Information
复制标题
DOI：
10.1109/cvpr.2018.00455
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Shixing Chen;Caojin Zhang;Ming Dong
中科院分区：
文献类型：
--
作者：
Shixing Chen;Caojin Zhang;Ming Dong
在迁移学习中，人们寻求从具有足够数据的源任务中迁移相关信息，以帮助只有有限数据的目标任务的学习。在本文中，我们提出了一种新的耦合端到端迁移学习（CETL）框架，该框架主要由两个卷积神经网络（源和目标）组成，它们连接到一个共享解码器。一种新的损失函数，耦合损失，被用于CETL训练。从理论的角度出发，我们通过建立CETL的学习边界来论证耦合损失的基本原理。此外，我们还引入了广义Fisher信息来改进CETL中的多任务优化。从实用角度看，CETL为领域自适应、知识升华等各种学习任务提供了统一的、高度灵活的解决方案。实验结果表明，该方法在跨域、跨任务图像分类方面具有优异的性能。
In transfer learning, one seeks to transfer related information from source tasks with sufficient data to help with the learning of target task with only limited data. In this paper, we propose a novel Coupled End-to-end Transfer Learning (CETL) framework, which mainly consists of two convolutional neural networks (source and target) that connect to a shared decoder. A novel loss function, the coupled loss, is used for CETL training. From a theoretical perspective, we demonstrate the rationale of the coupled loss by establishing a learning bound for CETL. Moreover, we introduce the generalized Fisher information to improve multi-task optimization in CETL. From a practical aspect, CETL provides a unified and highly flexible solution for various learning tasks such as domain adaption and knowledge distillation. Empirical result shows the superior performance of CETL on cross-domain and cross-task image classification.