Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation
This work addresses partial domain adaptation for machine learning applications where target domains have limited labeled data, representing an incremental improvement over existing methods.
The paper tackles partial domain adaptation, where knowledge is transferred from a larger source domain to a smaller target domain with fewer classes, by proposing a Discriminative Cross-Domain Feature Learning (DCDF) framework that iteratively optimizes target labels using weighted cross-domain center loss and graph propagation to align relevant source and target data, achieving effectiveness in recognition tasks as demonstrated on popular benchmarks.
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.