Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment

TL;DR

This paper introduces a semi-supervised domain generalization method for object detection that leverages vision-language pre-training and language space feature alignment, significantly improving performance across domains.

Contribution

It proposes a novel Cross-Domain Descriptive Multi-Scale Learning approach that aligns image descriptions in the language space to enhance domain generalization in object detection.

Findings

Achieves 11.7% improvement in DG setting

Achieves 7.5% improvement in DA setting

Outperforms existing methods significantly

Abstract

Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to distinguish between objects and achieve accurate detection. In this paper, we are the first to address the problem of semi-supervised domain generalization by exploring vision-language pre-training and enforcing feature alignment through the language space. We employ a novel Cross-Domain Descriptive Multi-Scale Learning (CDDMSL) aiming to maximize the agreement between descriptions of an image presented with different domain-specific characteristics in the embedding space. CDDMSL significantly outperforms existing methods, achieving 11.7% and 7.5% improvement in DG and DA settings, respectively. Comprehensive analysis and ablation studies confirm the effectiveness of our method, positioning CDDMSL as a promising approach for domain generalization in object detection tasks.