Instance-Free Domain Adaptive Object Detection

TL;DR

This paper introduces a novel approach for domain adaptive object detection that operates effectively without target domain object instances by leveraging background features and relational consistency.

Contribution

It proposes the RSCN method, pioneering background-based domain alignment and relational consistency, and curates new benchmarks for instance-free domain adaptation scenarios.

Findings

RSCN outperforms existing methods on three new benchmarks.

Effective domain adaptation without target object instances.

Relational and structural consistency improves detection accuracy.

Abstract

While Domain Adaptive Object Detection (DAOD) has made significant strides, most methods rely on unlabeled target data that is assumed to contain sufficient foreground instances. However, in many practical scenarios (e.g., wildlife monitoring, lesion detection), collecting target domain data with objects of interest is prohibitively costly, whereas background-only data is abundant. This common practical constraint introduces a significant technical challenge: the difficulty of achieving domain alignment when target instances are unavailable, forcing adaptation to rely solely on the target background information. We formulate this challenge as the novel problem of Instance-Free Domain Adaptive Object Detection. To tackle this, we propose the Relational and Structural Consistency Network (RSCN) which pioneers an alignment strategy based on background feature prototypes while simultaneously encouraging consistency in the relationship between the source foreground features and the background features within each domain, enabling robust adaptation even without target instances. To facilitate research, we further curate three specialized benchmarks, including simulative auto-driving detection, wildlife detection, and lung nodule detection. Extensive experiments show that RSCN significantly outperforms existing DAOD methods across all three benchmarks in the instance-free scenario. The code and benchmarks will be released soon.