The German Traffic Sign Recognition Benchmark: A multi-class classification competition

By Johannes Stallkamp, Marc Schlipsing, Jan Salmen, Christian Igel. 2011

1,371 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, methodology): “A includes datasets representing the aforementioned tasks, German Traffic Signs Recognition Benchmark (Stallkamp et al., 2011), as well as several other datasets adapted from VTAB (Zhai et al., 2019).”
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, background): “, 2021), Flowers102 (Nilsback & Zisserman, 2008), GTSRB (Stallkamp et al., 2011), UCF101 (Soomro et al.”
Multi-column deep neural networks for image classification (2012, methodology): “Here we train such nets by simple online back-propagation, setting new, greatly improved records on MNIST [19], Latin letters [13], Chinese characters [22], traffic signs [33], NORB (jittered, cluttered) [20] and CIFAR10 [17] benchmarks.”
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (2019, background): “Moreover, two of these datasets, Trafﬁc Signs and MSCOCO, are fully reserved for evaluation, meaning that no classes from them participate in the training set.”
Fast image scanning with deep max-pooling convolutional neural networks (2013, methodology): “Multi-Column DNN [8] improved previous results by over 30% on many benchmarks including: handwritten digits (MNIST) [4] and Latin letters (NIST SD 19) [9]; Chinese characters (CASIA) [10]; traﬃc signs (GTSRB) [11]; natural images (CIFAR 10) [12].”
Bypassing Backdoor Detection Algorithms in Deep Learning (2019, methodology): “2 color images, equally distributed amongst 10 mutually exclusive classes. Of these images, 50,000 are used for training, and 10,000 are used for testing. We also perform our experiments on the GTSRB [21] dataset of German traffic signs. It consists of over 51,839 color images, whose dimensions rang”
Overcoming catastrophic forgetting with hard attention to the task (2018, methodology): “The considered data sets are: CIFAR10 and CIFAR100 (Krizhevsky, 2009), FaceScrub (Ng & Winkler, 2014), FashionMNIST (Xiao et al., 2017), NotMNIST (Bulatov, 2011), MNIST (Le-Cun et al., 1998), SVHN (Netzer et al., 2011), and Traf-ﬁcSigns (Stallkamp et al., 2011).”
Federated Continual Learning with Weighted Inter-client Transfer (2020, methodology): “2) NonIID-50: We use the following eight benchmark datasets: MNIST (25), CIFAR-10/-100 (26), SVHN (27), FashionMNIST (28), Not-MNIST (29), FaceScrub (30), and TrafficSigns (31).”
Uncertainty-guided Continual Learning with Bayesian Neural Networks (2019, methodology): “…8 datasets with different distributions using the identical sequence as in (Serra et al., 2018), which includes FaceScrub (Ng & Winkler, 2014), MNIST, CIFAR100, NotMNIST (Bulatov, 2011), SVHN (Netzer et al., 2011), CIFAR10, TrafﬁcSigns (Stallkamp et al., 2011), and FashionMNIST (Xiao et al., 2017).”
Convolutional neural networks applied to house numbers digit classification (2012, neutral): “was also previously shown among others in a traffic sign classification challenge [14] where two independent teams obtained the best performance against various other approaches using ConvNets [12, 2].”
Knowledge-based Recurrent Attentive Neural Network for Traffic Sign Detection (2018, background): “However, those state-of-the-art methods [10], [12] at several popular datasets [13], [14] are not excellent at handling with small road signs recognition problem in a crowded scene with many other attractors like pedestrians and other vehicles.”
Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression (2017, methodology): “Experiments in this paper were conducted with convolutional neural networks on two image datasets: the CIFAR-10 dataset [10], and the German Traffic Sign Recognition Benchmark (GTSRB) dataset [23].”
CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition (2017, methodology): “It is a common practice to test the robustness of these systems with traffic datasets [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].”
Reproducible Scaling Laws for Contrastive Language-Image Learning (2022, background): “In addition, we fine-tune and evaluate on eight diverse datasets where zero-shot models perform poorly [55, 31]: Cars [41], DTD [14], EuroSAT [21], GTSRB [69], MNIST [44], RESISC45 [13], SUN397 [79], and SVHN [50].”