Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance

TL;DR

This paper introduces DIDM, a novel object detection model that balances domain-specific diversity and invariance, improving generalization to unseen domains by explicitly preserving domain-specific features during training.

Contribution

The paper proposes the Diversity Invariant Detection Model (DIDM) with modules that simultaneously promote domain invariance and preserve domain-specific information, addressing limitations of prior invariance-focused methods.

Findings

Outperforms existing methods on multiple datasets

Effectively balances domain invariance and diversity

Enhances feature representation for unseen domains

Abstract

Single-domain generalization for object detection (S-DGOD) seeks to transfer learned representations from a single source domain to unseen target domains. While recent approaches have primarily focused on achieving feature invariance, they ignore that domain diversity also presents significant challenges for the task. First, such invariance-driven strategies often lead to the loss of domain-specific information, resulting in incomplete feature representations. Second, cross-domain feature alignment forces the model to overlook domain-specific discrepancies, thereby increasing the complexity of the training process. To address these limitations, this paper proposes the Diversity Invariant Detection Model (DIDM), which achieves a harmonious integration of domain-specific diversity and domain invariance. Our key idea is to learn the invariant representations by keeping the inherent domain-specific features. Specifically, we introduce the Diversity Learning Module (DLM). This module limits the invariant semantics while explicitly enhancing domain-specific feature representation through a proposed feature diversity loss. Furthermore, to ensure cross-domain invariance without sacrificing diversity, we incorporate the Weighted Aligning Module (WAM) to enable feature alignment while maintaining the discriminative domain-specific information. Extensive experiments on multiple diverse datasets demonstrate the effectiveness of the proposed model, achieving superior performance compared to existing methods.