BuresNet: Conditional Bures Metric for Transferable Representation Learning
- 13 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (4) , 4198-4213
Abstract
As a fundamental manner for learning and cognition, transfer learning has attracted widespread attention in recent years. Typical transfer learning tasks include unsupervised domain adaptation (UDA) and few-shot learning (FSL), which both attempt to sufficiently transfer discriminative knowledge from the training environment to the test environment to improve the model's generalization performance. Previous transfer learning methods usually ignore the potential conditional distribution shift between environments. This leads to the discriminability degradation in the test environments. Therefore, how to construct a learnable and interpretable metric to measure and then reduce the gap between conditional distributions is very important in the literature. In this work, we design the Conditional Kernel Bures (CKB) metric for characterizing conditional distribution discrepancy, and derive an empirical estimation with convergence guarantee. CKB provides a statistical and interpretable approach, under the optimal transportation framework, to understand the knowledge transfer mechanism. It is essentially an extension of optimal transportation from the marginal distributions to the conditional distributions. CKB can be used as a plug-and-play module and placed onto the loss layer in deep networks, thus, it plays the bottleneck role in representation learning. From this perspective, the new method with network architecture is abbreviated as BuresNet, and it can be used extract conditional invariant features for both UDA and FSL tasks. BuresNet can be trained in an end-to-end manner. Extensive experiment results on several benchmark datasets validate the effectiveness of BuresNet.Keywords
Funding Information
- National Natural Science Foundation of China (61976229, 12026601)
- Open Research Projects of Zhejiang Lab (2021KH0AB08)
This publication has 40 references indexed in Scilit:
- Optimal Transport for Domain AdaptationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- A theory of learning from different domainsMachine Learning, 2009
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Kernel dimension reduction in regressionThe Annals of Statistics, 2009
- One-shot learning of object categoriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Learning and evaluating classifiers under sample selection bias2004
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000
- Joint measures and cross-covariance operatorsTransactions of the American Mathematical Society, 1973