CAFF-DINO: Multi-spectral object detection transformers with cross-attention features fusion

Open paper

Benchmark	Model	Rank	Results
multispectral-object-detection-on-flir	CAFF-DINO	–	mAP50: 85.5%mAP: 50.5%
pedestrian-detection-on-llvip	CAFF-DINO	–	AP: 0.685