Heterogeneous Domain Generalization via Domain Mixup

TL;DR

This paper introduces a novel domain mixup technique for heterogeneous domain generalization, enhancing deep CNNs' ability to recognize new categories across different domains, validated on the Visual Decathlon benchmark.

Contribution

The paper proposes a new sample mixing method across multiple source domains with two sampling strategies to improve domain generalization in deep CNNs.

Findings

Effective on Visual Decathlon benchmark

Improves recognition of novel categories across domains

Outperforms existing domain generalization methods

Abstract

One of the main drawbacks of deep Convolutional Neural Networks (DCNN) is that they lack generalization capability. In this work, we focus on the problem of heterogeneous domain generalization which aims to improve the generalization capability across different tasks, which is, how to learn a DCNN model with multiple domain data such that the trained feature extractor can be generalized to supporting recognition of novel categories in a novel target domain. To solve this problem, we propose a novel heterogeneous domain generalization method by mixing up samples across multiple source domains with two different sampling strategies. Our experimental results based on the Visual Decathlon benchmark demonstrates the effectiveness of our proposed method. The code is released in \url{https://github.com/wyf0912/MIXALL}