LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection

TL;DR

This paper introduces LAB-Det, a training-free method that uses language as a domain-invariant bridge to enable one-shot domain generalization in object detection without any model fine-tuning.

Contribution

LAB-Det leverages linguistic conditioning to adapt frozen detectors to new domains with only one exemplar per class, eliminating the need for training or parameter updates.

Findings

Achieves up to 5.4 mAP improvement over fine-tuned baselines.

Effective in data-scarce, specialized domains like underwater and industrial defect detection.

Demonstrates linguistic conditioning as an efficient alternative to fine-tuning.

Abstract

Foundation object detectors such as GLIP and Grounding DINO excel on general-domain data but often degrade in specialized and data-scarce settings like underwater imagery or industrial defects. Typical cross-domain few-shot approaches rely on fine-tuning scarce target data, incurring cost and overfitting risks. We instead ask: Can a frozen detector adapt with only one exemplar per class without training? To answer this, we introduce training-free one-shot domain generalization for object detection, where detectors must adapt to specialized domains with only one annotated exemplar per class and no weight updates. To tackle this task, we propose LAB-Det, which exploits Language As a domain-invariant Bridge. Instead of adapting visual features, we project each exemplar into a descriptive text that conditions and guides a frozen detector. This linguistic conditioning replaces gradient-based adaptation, enabling robust generalization in data-scarce domains. We evaluate on UODD (underwater) and NEU-DET (industrial defects), two widely adopted benchmarks for data-scarce detection, where object boundaries are often ambiguous, and LAB-Det achieves up to 5.4 mAP improvement over state-of-the-art fine-tuned baselines without updating a single parameter. These results establish linguistic adaptation as an efficient and interpretable alternative to fine-tuning in specialized detection settings.