Multi-column deep neural network for traffic sign classification

By Dan Claudiu Ciresan, Ueli Meier, Jonathan Masci, J. Urgen Schmidhuber. 2012

1,099 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

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

In Civil and Structural Engineering

1. Karol J. Piczak
2. Kyunghyun Cho
3. Victor S. Lempitsky
4. Yaroslav Ganin
5. Je-Won Kang
6. Alain Droniou
7. Olivier Sigaud
8. Min-Joo Kang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Trevor Darrell
5. Andrew Zisserman
6. Xiaogang Wang
7. Andrea Vedaldi
8. Jitendra Malik

In Human-Computer Interaction

1. Luc Van Gool
2. Peter Corke
3. Yoshua Bengio
4. Kyunghyun Cho
5. Karol J. Piczak
6. Klaus Greff
7. Aaron C. Courville
8. Victor S. Lempitsky

Citations in the corpus

• On the Number of Linear Regions of Deep Neural Networks (2014, background): “Artificial neural networks with several hidden layers, called deep neural networks, have become popular due to their unprecedented success in a variety of machine learning tasks (see, e.g., Krizhevsky et al. 2012, Ciresan et al. 2012, Goodfellow et al. 2013, Hinton et al. 2012).”
• Visualizing and Understanding Convolutional Networks (2013, background): “(Ciresan et al., 2012) demonstrate state-of-the-art performance on NORB and CIFAR-10 datasets.”
• Unsupervised Domain Adaptation by Backpropagation (2014, methodology): “We used the single-CNN baseline from (Cireşan et al., 2012) as our starting point.”
• Evidential Deep Learning to Quantify Classification Uncertainty (2018, background): “Further ramifications that adapt neural nets to particular applications have brought unprecedented prediction accuracies, which in certain cases exceed human-level performance [5, 4].”
• On the Binding Problem in Artificial Neural Networks (2020, background): “Modern neural networks have proven highly successful and superior to symbolic approaches in perceptual domains, such as in visual object recognition (Cireşan et al., 2011, 2012; Krizhevsky et al., 2012) or 1.”
• Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning (2014, background): “However, whereas the task of recognizing handwritten digits, traffic signs (Ciresan et al. , 2012) or faces ( ?”
• Crafting adversarial input sequences for recurrent neural networks (2016, background): “In such settings, the output data nature characterizes varying problems like classification [12], [13], [14], pattern recognition [15], or regression [16].”
• Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks (2013, background): “Convolutional neural networks which often employ max pooling have achieved state-of-the-art recognition performances on various benchmark datasets [20,9].”
• Self-Delimiting Neural Networks (2012, background): “[9] (5) ICDAR 2011 offline Chinese handwritten character recognition competition [10].”
• Probabilistic Object Detection: Definition and Evaluation (2018, background): “Mistakes in object detection could lead to catastrophic outcomes that not only risk the success of the robot’s mission, but potentially endanger human lives [1, 2, 24, 32, 35, 49].”