Quantum-Gated LiteSSD: A Parameter-Efficient Lightweight Hybrid Quantum-Classical Framework for Forward-Looking Sonar Object Detection

Niloy Kumar Mondal; Poulomi Sarker Puja

cs.CVSep 12, 2026

Quantum-Gated LiteSSD: A Parameter-Efficient Lightweight Hybrid Quantum-Classical Framework for Forward-Looking Sonar Object Detection

Authors: Niloy Kumar Mondal, Poulomi Sarker Puja

Organizations: Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh · Department of Urban and Regional Planning, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh

Abstract

Forward-looking sonar object detection is essential for underwater perception, yet deployment on embedded platforms requires highly compact models. To address this challenge, we explore quantum computing and introduce Quantum-Gated LiteSSD, a parameter-efficient hybrid quantum--classical detector that reformulates QuCNet-style multi-circuit quantum processing as an identity-centered channel-gating mechanism for spatial feature modulation. Experiments on the Marine Debris Watertank dataset and UATD forward-looking sonar benchmarks demonstrate an effective parameter--accuracy trade-off. The proposed detector achieves 90.84% $\mathrm{mAP}_{50}$ on Watertank with approximately $62\times$ fewer parameters than YOLO26s and $164.3\times$ fewer parameters than SSD-VGG16. On UATD, the model achieves 70.37% $\mathrm{mAP}_{50}$ with only 0.150M parameters, making it approximately $4.1\times$ smaller than SSGA-YOLO while retaining meaningful multi-class detection capability.

Figures & tables

Figure 1: Module-level and end-to-end pipeline of the proposed Quantum-Gated LiteSSD detector.

Architecture	Parameters (M)	mAP@50 (%)	Size Relative to Ours
YOLO26s [ 10 ]	$\approx 9.50$	94.79	$62.0\times$
SSD–VGG16 [ 19 ]	$\approx 25.18$	91.69	$164.3\times$
SSD–ResNet20 [ 5 ]	$\approx 4.52$	89.85	$29.5\times$
SSD–MobileNet [ 6 ]	$\approx 3.73$	70.30	$24.3\times$
SSD–DenseNet121 [ 7 ]	$\approx 3.50$	73.80	$22.9\times$
SSD–SqueezeNet [ 8 ]	$\approx 3.49$	68.37	$22.8\times$

Table 1: Comparison with SSD-based object detectors and YOLO26s on the Marine Debris Watertank dataset. The SSD mAP@50 results are reported by Valdenegro-Toro et al. [ 20 ] . Since that work does not report model sizes, the parameter counts of the SSD baselines are approximated from publicly available implementations of the corresponding backbone and detection architectures. The YOLO26s and QG-LiteSSD results are obtained from our experiments on the held-out test split.

Method	Parameters	mAP 50 (%)	mAP 50:95 (%)	Size vs. Ours
EfficientDet	6.56M	88.80	48.30	43.7 $\times$
SSD-MobileNet	3.73M	83.90	47.60	24.9 $\times$
YOLOv5n	1.77M	92.80	49.30	11.8 $\times$
YOLOv8n	3.01M	96.30	56.00	20.1 $\times$
YOLOv9-t	2.80M	96.40	56.30	18.7 $\times$
YOLOv10n	2.70M	96.60	56.50	18.0 $\times$

Table 2: Comparison with lightweight object detectors on the UATD dataset. Baseline results are the published values reported by Liu et al . [ 15 ] , whereas Quantum-Gated LiteSSD is evaluated using our implementation.

Efficient Object Detection

Efficient object detection reduces the computation, latency, memory, and energy needed to find and locate objects in images and video.

See all 95 papers

QYOLO: Lightweight Object Detection via Quantum Inspired Shared Channel Mixing
Apr 29, 2026Garvit Kumar Mittal, Sahil Tomar, Sandeep KumarEfficient Neural Network Inference Quantum-Inspired ML
Central Research Laboratory Bharat Electronics Limited Ghaziabad, India
MambaDSF: Multi-Scale SSM with Dilated Feature Fusion for Sonar Small Target Detection
May 24, 2026Hui Lin, Jiayi Li, Jing Wang +1Underwater Imaging Small Object Detection
School of Information Science and Engineering, Ocean University of China, Qingdao 266100, China · School of Information and Communication Technology, Griffith University, Nathan, QLD 4111, Australia
Quantum Feature Pyramid Gating for Seismic Image Segmentation
May 14, 2026Taha Gharaibeh, Jyotsna SharmaImage Segmentation Hybrid Quantum-Classical ML
Louisiana State University Baton Rouge, Louisiana, USA

Apr 29, 2026J/K move · Enter open · S save

QYOLO: Lightweight Object Detection via Quantum Inspired Shared Channel Mixing

Garvit Kumar Mittal, Sahil Tomar, Sandeep Kumar

Central Research Laboratory Bharat Electronics Limited Ghaziabad, India

Efficient Neural Network Inference Quantum-Inspired ML Object Detection Neural Network Compression

Open paper AskPDF arXiv

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.

Abstract

Efficient Object Detection

Explore similar work

QYOLO: Lightweight Object Detection via Quantum Inspired Shared Channel Mixing

MambaDSF: Multi-Scale SSM with Dilated Feature Fusion for Sonar Small Target Detection

Quantum Feature Pyramid Gating for Seismic Image Segmentation