Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection
By: Huizai Yao , Sicheng Zhao , Pengteng Li and more
Potential Business Impact:
Teaches computers to find objects in new places.
Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly rely on internal knowledge from the source model, which limits their capacity to generalize across domains and often results in biased pseudo-labels, thereby hindering both transferability and discriminability. In contrast, Vision Foundation Models (VFMs), pretrained on massive and diverse data, exhibit strong perception capabilities and broad generalization, yet their potential remains largely untapped in the SFOD setting. In this paper, we propose a novel SFOD framework that leverages VFMs as external knowledge sources to jointly enhance feature alignment and label quality. Specifically, we design three VFM-based modules: (1) Patch-weighted Global Feature Alignment (PGFA) distills global features from VFMs using patch-similarity-based weighting to enhance global feature transferability; (2) Prototype-based Instance Feature Alignment (PIFA) performs instance-level contrastive learning guided by momentum-updated VFM prototypes; and (3) Dual-source Enhanced Pseudo-label Fusion (DEPF) fuses predictions from detection VFMs and teacher models via an entropy-aware strategy to yield more reliable supervision. Extensive experiments on six benchmarks demonstrate that our method achieves state-of-the-art SFOD performance, validating the effectiveness of integrating VFMs to simultaneously improve transferability and discriminability.
Similar Papers
VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection
CV and Pattern Recognition
Finds objects in satellite pictures without original data.
VFM-Guided Semi-Supervised Detection Transformer for Source-Free Object Detection in Remote Sensing Images
CV and Pattern Recognition
Finds objects in satellite pictures without original data.
Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation
CV and Pattern Recognition
Uses multiple AI brains to improve computer vision.