Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization

TL;DR

This paper introduces SHADE, a unified framework that improves visual domain generalization by using style hallucination and dual consistency constraints to create style-diversified samples and maintain representation stability across domains.

Contribution

The paper proposes SHADE, a novel framework combining style hallucination with dual consistency constraints to enhance model generalization across unseen visual domains.

Findings

SHADE significantly improves generalization in image classification, segmentation, and detection.

The style hallucination module generates diverse, realistic styles during training.

SHADE outperforms existing methods across multiple models and tasks.

Abstract

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The domain shift mainly lies in the limited source environmental variations and the large distribution gap between source and unseen target data. To this end, we propose a unified framework, Style-HAllucinated Dual consistEncy learning (SHADE), to handle such domain shift in various visual tasks. Specifically, SHADE is constructed based on two consistency constraints, Style Consistency (SC) and Retrospection Consistency (RC). SC enriches the source situations and encourages the model to learn consistent representation across style-diversified samples. RC leverages general visual knowledge to prevent the model from overfitting to source data and thus largely keeps the representation consistent between the source and general visual models. Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning. SHM selects basis styles from the source distribution, enabling the model to dynamically generate diverse and realistic samples during training. Extensive experiments demonstrate that our versatile SHADE can significantly enhance the generalization in various visual recognition tasks, including image classification, semantic segmentation and object detection, with different models, i.e., ConvNets and Transformer.