Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation
arXiv:2008.11360
Abstract
Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes, which has attracted appealing attention. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain to better fight off the cross-domain distribution divergences. However, it is essential to align target data with only a small set of source data. In this paper, we develop a novel Discriminative Cross-Domain Feature Learning (DCDF) framework to iteratively optimize target labels with a cross-domain graph in a weighted scheme. Specifically, a weighted cross-domain center loss and weighted cross-domain graph propagation are proposed to couple unlabeled target data to related source samples for discriminative cross-domain feature learning, where irrelevant source centers will be ignored, to alleviate the marginal and conditional disparities simultaneously. Experimental evaluations on several popular benchmarks demonstrate the effectiveness of our proposed approach on facilitating the recognition for the unlabeled target domain, through comparing it to the state-of-the-art partial domain adaptation approaches.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Bridging Theory and Algorithm for Domain Adaptation
- Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
- Deep Residual Correction Network for Partial Domain Adaptation