GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder

TL;DR

GrabDAE introduces a novel unsupervised domain adaptation framework that leverages background blurring and denoising auto-encoders to improve feature alignment and classification accuracy across visual domains.

Contribution

The paper proposes GrabDAE, combining Grab-Mask and Denoising Auto-Encoder to enhance domain adaptation by focusing on relevant features and robust feature reconstruction.

Findings

Outperforms state-of-the-art UDA methods on benchmark datasets

Achieves significant improvements in classification accuracy

Demonstrates robustness and effectiveness across multiple visual domain tasks

Abstract

Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Domain Adaptation (UDA) methods often fall short in fully leveraging contextual information from the target domain, leading to suboptimal decision boundary separation during source and target domain alignment. To address this, we introduce GrabDAE, an innovative UDA framework designed to tackle domain shift in visual classification tasks. GrabDAE incorporates two key innovations: the Grab-Mask module, which blurs background information in target domain images, enabling the model to focus on essential, domain-relevant features through contrastive learning; and the Denoising Auto-Encoder (DAE), which enhances feature alignment by reconstructing features and filtering noise, ensuring a more robust adaptation to the target domain. These components empower GrabDAE to effectively handle unlabeled target domain data, significantly improving both classification accuracy and robustness. Extensive experiments on benchmark datasets, including VisDA-2017, Office-Home, and Office31, demonstrate that GrabDAE consistently surpasses state-of-the-art UDA methods, setting new performance benchmarks. By tackling UDA's critical challenges with its novel feature masking and denoising approach, GrabDAE offers both significant theoretical and practical advancements in domain adaptation.