# Road images augmentation with synthetic traffic signs using neural networks

arXiv: https://arxiv.org/abs/2101.04927 · HTML: https://mlsanity.com/paper/2101.04927/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 13 Jan 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [Modeling Visual Context is Key to Augmenting Object Detection Datasets](https://mlsanity.com/paper/1807.07428/) (2018)
- [Learning to Generate Synthetic Data via Compositing](https://mlsanity.com/paper/1904.05475/) (2019)
- [Context-Aware Synthesis and Placement of Object Instances](https://mlsanity.com/paper/1812.02350/) (2018)
- [Generative Modeling for Small-Data Object Detection](https://mlsanity.com/paper/1910.07169/) (2019)
- [PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection](https://mlsanity.com/paper/1608.08021/) (2016)
- [Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation](https://mlsanity.com/paper/1909.06436/) (2019)

## Built on by (most cited first, 3 of 3)

- [SQ-GAN: Semantic Image Communications Using Masked Vector Quantization](https://mlsanity.com/paper/2502.09520/) (2025)
- [Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes](https://mlsanity.com/paper/2303.01003/) (2023)
- [Enhancing Traffic Sign Recognition with Tailored Data Augmentation: Addressing Class Imbalance and Instance Scarcity](https://mlsanity.com/paper/2406.03576/) (2024)

## Abstract (arXiv)

Traffic sign recognition is a well-researched problem in computer vision. However, the state of the art methods works only for frequent sign classes, which are well represented in training datasets. We consider the task of rare traffic sign detection and classification. We aim to solve that problem by using synthetic training data. Such training data is obtained by embedding synthetic images of signs in the real photos. We propose three methods for making synthetic signs consistent with a scene in appearance. These methods are based on modern generative adversarial network (GAN) architectures. Our proposed methods allow realistic embedding of rare traffic sign classes that are absent in the training set. We adapt a variational autoencoder for sampling plausible locations of new traffic signs in images. We demonstrate that using a mixture of our synthetic data with real data improves the accuracy of both classifier and detector.