Search papers, labs, and topics across Lattice.
This paper presents a DPU-aware architecture tailored for attention-based YOLO variants, specifically YOLOv26 and YOLOv11, optimized for deployment on AMD FPGAs. By substituting unsupported activation functions and approximating the spatial attention mechanism, the authors achieve significant improvements in throughput and power efficiency while maintaining competitive accuracy across various benchmark datasets. The results show that the optimized models, YOLOv26n and YOLOv26n-OBB, reach up to 34.05 FPS with only a 5% drop in accuracy, demonstrating a potential for up to 3x lower power consumption compared to existing methods.
Achieving up to 34.05 FPS with only a 5% accuracy drop, this DPU-aware YOLO architecture redefines efficiency for edge-based object detection.
Edge-based Artificial Intelligence (AI) acceleration has recently improved progress in real-time object detection. Object detection on edge devices requires a balance between accuracy, speed, and power efficiency. This paper proposes a customized Deep Learning Processor Unit (DPU)-aware architecture for attention-based YOLO variants deployed on AMD FPGAs. Specifically, we evaluate and benchmark YOLOv26 and YOLOv11, two modern attention-based YOLO variants, on the Xilinx ZCU104 across both standard and oriented object detection tasks. We replace unsupported activation functions, substitute split operations with 1x1 convolutions, and approximate the spatial attention mechanism in a DPU-compatible way. All models are then trained and evaluated across six benchmark datasets such as COCO, Pascal VOC, KITTI, DOTA, DIOR-R, and an in-house human presence dataset, and benchmarked across all eight DPU configurations (B512 to B4096) in terms of mAP, FPS, latency, power, and resource utilization. Notably, YOLOv26n and YOLOv26n-OBB deliver the highest end-to-end throughput at 34.05 and 29.55 FPS for standard and oriented detection, respectively, with an average of 5% absolute reduction in accuracy due to quantization while achieving up to approximately 3x lower power consumption compared with the state of the art.
