A frozen-backbone framework that uses pretrained DINOv3 register tokens as a bidirectional cross-modal bottleneck reports the highest mAP50-95 on LLVIP, M3FD, DroneVehicle, and FLIR-Aligned among the compared methods.
DINOv2: Learning robust visual features without supervi- sion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection
A frozen-backbone framework that uses pretrained DINOv3 register tokens as a bidirectional cross-modal bottleneck reports the highest mAP50-95 on LLVIP, M3FD, DroneVehicle, and FLIR-Aligned among the compared methods.