QYOLO: Lightweight Object Detection via Quantum Inspired Shared Channel Mixing

TL;DR

QYOLO introduces a quantum-inspired channel mixing method that significantly reduces model size and computation in object detection while maintaining accuracy, enabling more efficient real-time applications.

Contribution

This work presents a novel quantum-inspired shared channel mixing framework replacing deep backbone modules, achieving architectural compression with minimal accuracy loss.

Findings

QYOLOv8n reduces parameters by 20.2% with 0.4 pp mAP@50 degradation.

QYOLOv8s achieves 21.8% parameter reduction with 0.1 pp mAP@50 degradation.

Combined with distillation, full accuracy parity is recovered at no additional cost.

Abstract

The rapid advancement of object detection architectures has positioned single stage detectors as the dominant solution for real-time visual perception. A primary source of computational overhead in these models lies in the deep backbone stages, where C2f bottleneck modules at high stride levels accumulate a disproportionate share of parameters due to quadratic scaling with channel width. This work introduces QYOLO, a quantum-inspired channel mixing framework that achieves genuine architectural compression by replacing the two deepest backbone C2f modules at P4/16 (512 channels) and P5/32 (1024 channels) with a compact QMixBlock. The proposed block performs global channel recalibration through a sinusoidal mixing mechanism with shared learnable parameters across both backbone stages, enforcing consistent channel importance without requiring independent per-stage parameter sets. The neck and detection head remain fully classical and unchanged. Evaluation on the VisDrone2019 benchmark demonstrates that QYOLOv8n achieves a 20.2% reduction in parameter count (3.01M to 2.40M) and 12.3% GFLOPs reduction with only 0.4 pp mAP@50 degradation. QYOLOv8s achieves 21.8% reduction with 0.1 pp degradation. When combined with knowledge distillation, full accuracy parity is recovered at no cost to compression. An expanded backbone plus neck variant achieved 38 to 41% reduction at the cost of greater accuracy degradation, motivating the backbone-only final design.