DSC-Mamba: a lightweight dual-attention network for real-time driver behavior detection

This paper presents DSC-Mamba, a lightweight model for abnormal driving behavior detection from in-vehicle camera images. The model reduces computational load through depthwise separable convolution and designs two key interaction mechanisms: in the DAEDC module, channel attention generates weights to modulate multi-scale spatial attention; in the HEMamba module, the global modeling output of Mamba is normalized and re-injected into local tokens, allowing global context to calibrate local representations. On the SFD3 dataset, using driver-level five-fold cross-validation as the primary protocol, DSC-Mamba achieved an average accuracy of 93.12% ± 0.19% with only 0.421 M parameters and 0.1053 G FLOPs. This is 0.08 percentage points higher than the competitive MVim baseline under the same partition. Under random image-level partitioning, the accuracy reached 99.89%, though this is noted as overly optimistic and for reference only. On the AUCv2 dataset, the model achieved 92.75% accuracy. Furthermore, PyTorchSim-based NPU simulation estimates an INT8 single-frame latency of 12–18 ms and power consumption of 0.9–1.4 W. These results indicate that DSC-Mamba achieves a favorable balance among parameter count, FLOPs, and accuracy, though real-vehicle hardware verification remains future work.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-17
DOI
https://doi.org/10.1038/s41598-026-80085-0
Primary Topic
Advanced Neural Network Applications
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

DSC-Mamba: a lightweight dual-attention network for real-time driver behavior detection

Jingjiao Chen, Shanshan He, Chengjun Xu
5 links
Scientific Reports
Advanced Neural Network Applications
article

DSC-Mamba: a lightweight dual-attention network for real-time driver behavior detection

Jingjiao Chen, Shanshan He, Chengjun Xu
article en

Abstract

This paper presents DSC-Mamba, a lightweight model for abnormal driving behavior detection from in-vehicle camera images. The model reduces computational load through depthwise separable convolution and designs two key interaction mechanisms: in the DAEDC module, channel attention generates weights to modulate multi-scale spatial attention; in the HEMamba module, the global modeling output of Mamba is normalized and re-injected into local tokens, allowing global context to calibrate local representations. On the SFD3 dataset, using driver-level five-fold cross-validation as the primary protocol, DSC-Mamba achieved an average accuracy of 93.12% ± 0.19% with only 0.421 M parameters and 0.1053 G FLOPs. This is 0.08 percentage points higher than the competitive MVim baseline under the same partition. Under random image-level partitioning, the accuracy reached 99.89%, though this is noted as overly optimistic and for reference only. On the AUCv2 dataset, the model achieved 92.75% accuracy. Furthermore, PyTorchSim-based NPU simulation estimates an INT8 single-frame latency of 12–18 ms and power consumption of 0.9–1.4 W. These results indicate that DSC-Mamba achieves a favorable balance among parameter count, FLOPs, and accuracy, though real-vehicle hardware verification remains future work.

Scientific Reports
Wuhan University (CN), Anhui Sanlian University (CN), Jiangxi Normal University (CN)
National Natural Science Foundation of China
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon