Domain Adaptation with L2 constraints for classifying images from different endoscope systems

TL;DR

This paper introduces MMDTL2, a domain adaptation method that incorporates L2 constraints to improve image classification across different endoscope systems, demonstrating superior performance over existing methods.

Contribution

The paper extends the MMDT approach by adding L2 constraints and derives a more efficient dual formulation for domain adaptation in endoscopic image classification.

Findings

MMDTL2 outperforms MMDT and SVM without adaptation.

Effective for high-dimensional NBI image features.

Works well with more than 20 training samples per class.

Abstract

This paper proposes a method for domain adaptation that extends the maximum margin domain transfer (MMDT) proposed by Hoffman et al., by introducing L2 distance constraints between samples of different domains; thus, our method is denoted as MMDTL2. Motivated by the differences between the images taken by narrow band imaging (NBI) endoscopic devices, we utilize different NBI devices as different domains and estimate the transformations between samples of different domains, i.e., image samples taken by different NBI endoscope systems. We first formulate the problem in the primal form, and then derive the dual form with much lesser computational costs as compared to the naive approach. From our experimental results using NBI image datasets from two different NBI endoscopic devices, we find that MMDTL2 is better than MMDT and also support vector machines without adaptation, especially when NBI image features are high-dimensional and the per-class training samples are greater than 20.