Q-YOLO: Efficient Inference for Real-time Object Detection
This research enables more efficient deployment of object detection models on resource-constrained edge devices, though it is incremental as it builds upon existing quantization methods.
The paper tackled the problem of performance degradation in quantized YOLO models for real-time object detection by proposing Q-YOLO, a low-bit quantization method that uses a Unilateral Histogram-based activation quantization scheme to minimize errors, resulting in improved accuracy and computational efficiency on the COCO dataset.
Real-time object detection plays a vital role in various computer vision applications. However, deploying real-time object detectors on resource-constrained platforms poses challenges due to high computational and memory requirements. This paper describes a low-bit quantization method to build a highly efficient one-stage detector, dubbed as Q-YOLO, which can effectively address the performance degradation problem caused by activation distribution imbalance in traditional quantized YOLO models. Q-YOLO introduces a fully end-to-end Post-Training Quantization (PTQ) pipeline with a well-designed Unilateral Histogram-based (UH) activation quantization scheme, which determines the maximum truncation values through histogram analysis by minimizing the Mean Squared Error (MSE) quantization errors. Extensive experiments on the COCO dataset demonstrate the effectiveness of Q-YOLO, outperforming other PTQ methods while achieving a more favorable balance between accuracy and computational cost. This research contributes to advancing the efficient deployment of object detection models on resource-limited edge devices, enabling real-time detection with reduced computational and memory overhead.