Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation

TL;DR

This paper introduces a novel framework for partial domain adaptation that enhances feature learning by iteratively aligning target data with relevant source data using a weighted graph and center loss, improving recognition accuracy.

Contribution

The paper proposes a Discriminative Cross-Domain Feature Learning (DCDF) framework with weighted graph propagation and center loss to better align target and source data in partial domain adaptation.

Findings

Outperforms state-of-the-art partial domain adaptation methods.

Effectively reduces marginal and conditional distribution disparities.

Improves recognition accuracy on benchmark datasets.

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.