Domain Adaptive Neural Networks for Object Recognition

TL;DR

This paper introduces a neural network model that uses Maximum Mean Discrepancy (MMD) regularization to improve domain adaptation in object recognition tasks, demonstrating effectiveness on image datasets.

Contribution

It is the first to incorporate MMD regularization into neural networks for domain adaptation, combined with denoising auto-encoder pretraining for enhanced performance.

Findings

MMD regularization improves domain adaptation performance.

Pretraining with denoising auto-encoders enhances results.

The model outperforms recent benchmarks on specific datasets.

Abstract

We propose a simple neural network model to deal with the domain adaptation problem in object recognition. Our model incorporates the Maximum Mean Discrepancy (MMD) measure as a regularization in the supervised learning to reduce the distribution mismatch between the source and target domains in the latent space. From experiments, we demonstrate that the MMD regularization is an effective tool to provide good domain adaptation models on both SURF features and raw image pixels of a particular image data set. We also show that our proposed model, preceded by the denoising auto-encoder pretraining, achieves better performance than recent benchmark models on the same data sets. This work represents the first study of MMD measure in the context of neural networks.