Octave-YOLO: Cross frequency detection network with octave convolution

TL;DR

Octave-YOLO introduces a cross frequency detection network that efficiently processes high-resolution images in real-time on embedded devices by dividing features into frequency-based sections, reducing computation while maintaining accuracy.

Contribution

The paper proposes Octave-YOLO with CFPNet, enabling real-time high-resolution object detection on embedded systems through frequency-based feature separation and efficient convolution techniques.

Findings

Matches YOLOv8 performance with 40% fewer parameters

1.56x faster than YOLOv8 at 1080x1080 resolution

Significantly reduces computational demands while maintaining accuracy

Abstract

Despite the rapid advancement of object detection algorithms, processing high-resolution images on embedded devices remains a significant challenge. Theoretically, the fully convolutional network architecture used in current real-time object detectors can handle all input resolutions. However, the substantial computational demands required to process high-resolution images render them impractical for real-time applications. To address this issue, real-time object detection models typically downsample the input image for inference, leading to a loss of detail and decreased accuracy. In response, we developed Octave-YOLO, designed to process high-resolution images in real-time within the constraints of embedded systems. We achieved this through the introduction of the cross frequency partial network (CFPNet), which divides the input feature map into low-resolution, low-frequency, and high-resolution, high-frequency sections. This configuration enables complex operations such as convolution bottlenecks and self-attention to be conducted exclusively on low-resolution feature maps while simultaneously preserving the details in high-resolution maps. Notably, this approach not only dramatically reduces the computational demands of convolution tasks but also allows for the integration of attention modules, which are typically challenging to implement in real-time applications, with minimal additional cost. Additionally, we have incorporated depthwise separable convolution into the core building blocks and downsampling layers to further decrease latency. Experimental results have shown that Octave-YOLO matches the performance of YOLOv8 while significantly reducing computational demands. For example, in 1080x1080 resolution, Octave-YOLO-N is 1.56 times faster than YOLOv8, achieving nearly the same accuracy on the COCO dataset with approximately 40 percent fewer parameters and FLOPs.