SiStNet: A Single-Stage Convolutional Neural Network for Vehicle Detection

In this study, we propose SiStNet, a single-stage deep learning architecture for vehicle detection in autonomous driving scenarios. The proposed architecture is trained entirely from scratch on domain-specific data without relying on pretrained backbones and is evaluated against representative baseline detectors under identical training conditions. Experiments are conducted on the KITTI dataset under a consistent training and evaluation protocol. An ablation study conducted under a reduced training budget (20% of data, 30 epochs) revealed that multi-scale detection, data augmentation, and anchor-based prediction did not contribute positively to detection performance under the given training conditions. Based on these findings, the final SiStNet architecture was simplified by removing these three components and re-trained under the full training budget. The resulting model achieves a mean Average Precision (mAP) of 0.5033±0.0072 and a recall of 0.6935±0.0214, representing substantial improvements over the initially reported values (0.3896 and 0.439, respectively). The inference speed of SiStNet is 24.41±0.02 FPS, which satisfies the real-time threshold of 20 FPS defined in this study. The model achieves lower mAP than baseline detectors that employ larger and deeper architectures; all models were trained from scratch under identical conditions, so the accuracy gap reflects architectural capacity differences rather than pretraining advantages. SiStNet is presented as a domain-specific, scratch-trained alternative that achieves competitive detection performance without reliance on large-scale pretraining, at the cost of lower mAP relative to deeper baselines.