Quantization of Faster R-CNN

The Faster Region-based Convolutional Network (Faster R-CNN) is an efficient object detection model. However, its large size and significant computational requirements limit its applicability in embedded systems and real-time environments. Quantization is a proven method for reducing models’ size and computational requirements, but there is currently no open-source general implementation for quantizing Faster R-CNN. The main reason is that individual architecture components need to be quantized separately due to their structural characteristics. We present a general Faster R-CNN quantization algorithm, for which our implementation is open-source and compatible with the PyTorch (2.7.0+cu126, pt12) ecosystem. Our solution reduces the model size by 67.2% and the detection time by 50.4% while maintaining the accuracy measured on the test data within an error margin of 8.2% and a standard deviation of ±3.4%. It also allows for the visualization of model errors by extracting the model’s internal activation maps, supporting a more efficient understanding of its behavior. We demonstrate that the proposed method can effectively quantize Faster R-CNN, enabling the model to run on low-power hardware. This is particularly important in applications such as autonomous vehicles, embedded sensor systems, and real-time security surveillance, where fast and energy-efficient object detection is crucial.