Multi-Representation Adaptation Network for Cross-domain Image Classification

TL;DR

This paper introduces a multi-representation adaptation network that aligns multiple feature representations from different aspects to improve cross-domain image classification accuracy, leveraging a hybrid Inception Adaptation Module and an extended MMD loss.

Contribution

It proposes a novel multi-representation adaptation framework with a hybrid structure and an extended MMD loss for better domain alignment in image classification.

Findings

Significant accuracy improvements on three benchmark datasets.

Effective multi-representation alignment via the proposed IAM.

Easy integration with existing models through extension of feed-forward architectures.

Abstract

In image classification, it is often expensive and time-consuming to acquire sufficient labels. To solve this problem, domain adaptation often provides an attractive option given a large amount of labeled data from a similar nature but different domain. Existing approaches mainly align the distributions of representations extracted by a single structure and the representations may only contain partial information, e.g., only contain part of the saturation, brightness, and hue information. Along this line, we propose Multi-Representation Adaptation which can dramatically improve the classification accuracy for cross-domain image classification and specially aims to align the distributions of multiple representations extracted by a hybrid structure named Inception Adaptation Module (IAM). Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects. In addition, we extend Maximum Mean Discrepancy (MMD) to compute the adaptation loss. Our approach can be easily implemented by extending most feed-forward models with IAM, and the network can be trained efficiently via back-propagation. Experiments conducted on three benchmark image datasets demonstrate the effectiveness of MRAN. The code has been available at https://github.com/easezyc/deep-transfer-learning.