Efficient Multi-Domain Network Learning by Covariance Normalization
arXiv:1906.10267
Abstract
The problem of multi-domain learning of deep networks is considered. An adaptive layer is induced per target domain and a novel procedure, denoted covariance normalization (CovNorm), proposed to reduce its parameters. CovNorm is a data driven method of fairly simple implementation, requiring two principal component analyzes (PCA) and fine-tuning of a mini-adaptation layer. Nevertheless, it is shown, both theoretically and experimentally, to have several advantages over previous approaches, such as batch normalization or geometric matrix approximations. Furthermore, CovNorm can be deployed both when target datasets are available sequentially or simultaneously. Experiments show that, in both cases, it has performance comparable to a fully fine-tuned network, using as few as 0.13% of the corresponding parameters per target domain.
10 Pages Accepted by CVPR 2019
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Transferable Features with Deep Adaptation Networks
- Fine-Grained Visual Classification of Aircraft
- A Survey on Multi-Task Learning
- Domain Separation Networks
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- Overcoming Catastrophic Forgetting by Incremental Moment Matching
- Universal representations:The missing link between faces, text, planktons, and cat breeds