# Traffic Sign Classification Using Deep Inception Based Convolutional Networks

arXiv: https://arxiv.org/abs/1511.02992 · HTML: https://mlsanity.com/paper/1511.02992/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2015.

## Built on by (most cited first, 6 of 6)

- [Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization](https://mlsanity.com/paper/2411.00392/) (2024)
- [Traffic Sign Recognition Using Local Vision Transformer](https://mlsanity.com/paper/2311.06651/) (2023)
- [Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning](https://mlsanity.com/paper/2605.01046/) (2026)
- [Symbolic Perception Risk in Autonomous Driving](https://mlsanity.com/paper/2303.09416/) (2023)
- [Benchmarking Nighttime Traffic Sign Recognition with Illumination-Adaptive Detection and Semantic Attribute Reasoning](https://mlsanity.com/paper/2511.17183/) (2025)
- [Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder](https://mlsanity.com/paper/2603.05528/) (2026)

## Abstract (arXiv)

In this work, we propose a novel deep network for traffic sign classification that achieves outstanding performance on GTSRB surpassing all previous methods. Our deep network consists of spatial transformer layers and a modified version of inception module specifically designed for capturing local and global features together. This features adoption allows our network to classify precisely intraclass samples even under deformations. Use of spatial transformer layer makes this network more robust to deformations such as translation, rotation, scaling of input images. Unlike existing approaches that are developed with hand-crafted features, multiple deep networks with huge parameters and data augmentations, our method addresses the concern of exploding parameters and augmentations. We have achieved the state-of-the-art performance of 99.81% on GTSRB dataset.