Associative Domain Adaptation

TL;DR

This paper introduces associative domain adaptation, a neural network technique that aligns source and target domain embeddings to improve label inference in unlabeled target data, achieving state-of-the-art results.

Contribution

It presents a simple, effective association loss for end-to-end domain adaptation that enhances embedding invariance and can be integrated into existing networks with minimal overhead.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Produces more effective domain-invariant embeddings.

Outperforms MMD-based methods in domain adaptation tasks.

Abstract

We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source domain. Our training scheme follows the paradigm that in order to effectively derive class labels for the target domain, a network should produce statistically domain invariant embeddings, while minimizing the classification error on the labeled source domain. We accomplish this by reinforcing associations between source and target data directly in embedding space. Our method can easily be added to any existing classification network with no structural and almost no computational overhead. We demonstrate the effectiveness of our approach on various benchmarks and achieve state-of-the-art results across the board with a generic convolutional neural network architecture not specifically tuned to the respective tasks. Finally, we show that the proposed association loss produces embeddings that are more effective for domain adaptation compared to methods employing maximum mean discrepancy as a similarity measure in embedding space.