# SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection

arXiv: https://arxiv.org/abs/1804.00433 · HTML: https://mlsanity.com/paper/1804.00433/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2018.

## Built on by (most cited first, 18 of 18)

- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Deep Texture-Aware Features for Camouflaged Object Detection](https://mlsanity.com/paper/2102.02996/) (2021)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)
- [Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor](https://mlsanity.com/paper/2204.13349/) (2022)
- [Visible and Clear: Finding Tiny Objects in Difference Map](https://mlsanity.com/paper/2405.11276/) (2024)
- [LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image](https://mlsanity.com/paper/2110.15045/) (2021)
- [ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentation](https://mlsanity.com/paper/2201.11523/) (2022)
- [Smart Traffic Management of Vehicles using Faster R-CNN based Deep Learning Method](https://mlsanity.com/paper/2311.10099/) (2023)
- [Bangladeshi Native Vehicle Detection in Wild](https://mlsanity.com/paper/2405.12150/) (2024)
- [All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles](https://mlsanity.com/paper/2510.26641/) (2025)
- [Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images](https://mlsanity.com/paper/2104.08126/) (2021)
- [Orientation Aware Weapons Detection In Visual Data : A Benchmark Dataset](https://mlsanity.com/paper/2112.02221/) (2021)
- [Semi-MoreGAN: A New Semi-supervised Generative Adversarial Network for Mixture of Rain Removal](https://mlsanity.com/paper/2204.13420/) (2022)
- [Robust and Fast Vehicle Detection using Augmented Confidence Map](https://mlsanity.com/paper/2304.14462/) (2023)
- [A Dynamic Transformer Network for Vehicle Detection](https://mlsanity.com/paper/2506.02765/) (2025)
- [CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects](https://mlsanity.com/paper/2506.09897/) (2025)
- [A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance](https://mlsanity.com/paper/2510.20016/) (2025)

## Abstract (arXiv)

Vision-based vehicle detection approaches achieve incredible success in recent years with the development of deep convolutional neural network (CNN). However, existing CNN based algorithms suffer from the problem that the convolutional features are scale-sensitive in object detection task but it is common that traffic images and videos contain vehicles with a large variance of scales. In this paper, we delve into the source of scale sensitivity, and reveal two key issues: 1) existing RoI pooling destroys the structure of small scale objects, 2) the large intra-class distance for a large variance of scales exceeds the representation capability of a single network. Based on these findings, we present a scale-insensitive convolutional neural network (SINet) for fast detecting vehicles with a large variance of scales. First, we present a context-aware RoI pooling to maintain the contextual information and original structure of small scale objects. Second, we present a multi-branch decision network to minimize the intra-class distance of features. These lightweight techniques bring zero extra time complexity but prominent detection accuracy improvement. The proposed techniques can be equipped with any deep network architectures and keep them trained end-to-end. Our SINet achieves state-of-the-art performance in terms of accuracy and speed (up to 37 FPS) on the KITTI benchmark and a new highway dataset, which contains a large variance of scales and extremely small objects.