# Pyramid Transformer for Traffic Sign Detection

arXiv: https://arxiv.org/abs/2207.06067 · HTML: https://mlsanity.com/paper/2207.06067/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 13 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics](https://mlsanity.com/paper/1908.11262/) (2019)
- [VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection](https://mlsanity.com/paper/1905.01583/) (2019)
- [Patchwise object tracking via structural local sparse appearance model](https://mlsanity.com/paper/1803.06141/) (2018)

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

- [Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Context](https://mlsanity.com/paper/2301.05804/) (2023)
- [Robust Transformer with Locality Inductive Bias and Feature Normalization](https://mlsanity.com/paper/2301.11553/) (2023)
- [Traffic Sign Recognition Using Local Vision Transformer](https://mlsanity.com/paper/2311.06651/) (2023)
- [Efficient Vision Transformer for Accurate Traffic Sign Detection](https://mlsanity.com/paper/2311.01429/) (2023)
- [Cross-domain Multi-step Thinking: Zero-shot Fine-grained Traffic Sign Recognition in the Wild](https://mlsanity.com/paper/2409.01534/) (2024)
- [Squeeze-Aware-YOLO: Early Channel Recalibration and Multi-Scale Fusion for Real-Time Traffic Sign Detection](https://mlsanity.com/paper/2610.15604/) (2026)

## Abstract (arXiv)

Traffic sign detection is a vital task in the visual system of self-driving cars and the automated driving system. Recently, novel Transformer-based models have achieved encouraging results for various computer vision tasks. We still observed that vanilla ViT could not yield satisfactory results in traffic sign detection because the overall size of the datasets is very small and the class distribution of traffic signs is extremely unbalanced. To overcome this problem, a novel Pyramid Transformer with locality mechanisms is proposed in this paper. Specifically, Pyramid Transformer has several spatial pyramid reduction layers to shrink and embed the input image into tokens with rich multi-scale context by using atrous convolutions. Moreover, it inherits an intrinsic scale invariance inductive bias and is able to learn local feature representation for objects at various scales, thereby enhancing the network robustness against the size discrepancy of traffic signs. The experiments are conducted on the German Traffic Sign Detection Benchmark (GTSDB). The results demonstrate the superiority of the proposed model in the traffic sign detection tasks. More specifically, Pyramid Transformer achieves 77.8% mAP on GTSDB when applied to the Cascade RCNN as the backbone, which surpasses most well-known and widely-used state-of-the-art models.