Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher

TL;DR

This paper introduces Prototype-based Mean Teacher (PMT), a novel multi-source domain adaptation method for object detection that uses class prototypes to encode domain-specific information, reducing parameter growth and improving accuracy.

Contribution

PMT leverages class prototypes instead of domain-specific subnets, enabling scalable adaptation across multiple source domains with fewer parameters and enhanced detection performance.

Findings

PMT outperforms state-of-the-art MSDA methods on several datasets.

Prototypes effectively encode domain-specific information without increasing parameters.

The method reduces memory usage and overfitting risks.

Abstract

Adapting visual object detectors to operational target domains is a challenging task, commonly achieved using unsupervised domain adaptation (UDA) methods. Recent studies have shown that when the labeled dataset comes from multiple source domains, treating them as separate domains and performing a multi-source domain adaptation (MSDA) improves the accuracy and robustness over blending these source domains and performing a UDA. For adaptation, existing MSDA methods learn domain-invariant and domain-specific parameters (for each source domain). However, unlike single-source UDA methods, learning domain-specific parameters makes them grow significantly in proportion to the number of source domains. This paper proposes a novel MSDA method called Prototype-based Mean Teacher (PMT), which uses class prototypes instead of domain-specific subnets to encode domain-specific information. These prototypes are learned using a contrastive loss, aligning the same categories across domains and separating different categories far apart. Given the use of prototypes, the number of parameters required for our PMT method does not increase significantly with the number of source domains, thus reducing memory issues and possible overfitting. Empirical studies indicate that PMT outperforms state-of-the-art MSDA methods on several challenging object detection datasets. Our code is available at https://github.com/imatif17/Prototype-Mean-Teacher.