Robust Visual Knowledge Transfer via EDA

TL;DR

This paper introduces EDA, a robust cross-domain visual classification framework using extreme learning machines, integrating labeled source and limited target data, with manifold regularization and multi-view modeling, outperforming existing methods.

Contribution

The paper proposes a novel EDA framework that combines ELM-based domain adaptation with manifold regularization and multi-view modeling for improved visual knowledge transfer.

Findings

Outperforms existing cross-domain learning methods on benchmark datasets.

Effectively integrates unlabeled target data to enhance stability.

Demonstrates robustness in video event and object recognition tasks.

Abstract

We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme learning machine based cross-domain network learning framework, that is called Extreme Learning Machine (ELM) based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the l_(2,1)-norm of the network output weights and the learning error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross domain learning. It minimizes the matching error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as base classifiers. The network output weights cannot only be analytically determined, but also transferrable. Additionally, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semi-supervised learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition, demonstrate that our EDA methods outperform existing cross-domain learning methods.