M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning

TL;DR

M-ADDA introduces a novel unsupervised domain adaptation method combining metric learning and adversarial training, leading to improved classification accuracy on digit datasets by creating well-structured feature clusters.

Contribution

The paper proposes M-ADDA, a new approach that integrates metric learning with adversarial domain adaptation to enhance feature clustering and classification performance.

Findings

M-ADDA outperforms ADDA on MNIST and USPS datasets.

Metric learning improves domain adaptation accuracy.

The approach effectively creates discriminative feature clusters.

Abstract

Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from a slightly similar distribution. We propose metric-based adversarial discriminative domain adaptation (M-ADDA) which performs two main steps. First, it uses a metric learning approach to train the source model on the source dataset by optimizing the triplet loss function. This results in clusters where embeddings of the same label are close to each other and those with different labels are far from one another. Next, it uses the adversarial approach (as that used in ADDA \cite{2017arXiv170205464T}) to make the extracted features from the source and target datasets indistinguishable. Simultaneously, we optimize a novel loss function that encourages the target dataset's embeddings to form clusters. While ADDA and M-ADDA use similar architectures, we show that M-ADDA performs significantly better on the digits adaptation datasets of MNIST and USPS. This suggests that using metric-learning for domain adaptation can lead to large improvements in classification accuracy for the domain adaptation task. The code is available at \url{https://github.com/IssamLaradji/M-ADDA}.