Instance-Free Domain Adaptive Object Detection

2026-02-06

AI Summary

This work addresses the practical challenge of domain adaptation in object detection when the target domain contains only background data and no foreground instances. It introduces, for the first time, the problem of "instance-free domain adaptive object detection" and proposes a Relation and Structure Consistency Network (RSCN). The method achieves cross-domain alignment solely using background feature prototypes from the target domain while enforcing semantic relation consistency between foreground and background regions in the source domain. Key contributions include a novel alignment strategy, the construction of three dedicated benchmark datasets, and consistent outperformance over existing methods across diverse applications—autonomous driving simulation, wildlife monitoring, and pulmonary nodule detection—demonstrating its effectiveness in scenarios devoid of target-domain object instances.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Object Detection & Categorization
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

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.

Problem

• Domain Adaptive Object Detection
• Instance-Free
• Target Domain
• Background-Only Data
• Domain Alignment

Innovation

• Instance-Free DAOD
• Background Prototype Alignment
• Relational Consistency
• Domain Adaptation
• Object Detection