Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks

By Junqi Jin, Kun Fu, Changshui Zhang. IEEE transactions on intelligent transportation systems (Print), 2014

312 citations recorded by the source corpus.

How researchers see this paper

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

Beyond Sharing Weights for Deep Domain Adaptation (2016, background): “form the logistic loss in practice for some tasks [61], [62].”
Perceptual Generative Adversarial Networks for Small Object Detection (2017, background): “[19] proposed to train the CNN with hingle loss, which provides better test accuracy and faster stable convergence.”
Traffic Sign Recognition via Multi-Modal Tree-Structure Embedded Multi-Task Learning (2017, methodology): “Recently, Jin et al. [20] proposed the hinge loss trained CNN method, and achieved the best accuracy of 99.65% over the best record 99.46% kept by Dan Ciresan.”
Deep Learning for Large-Scale Traffic-Sign Detection and Recognition (2019, methodology): “In TSR, CNNs have been used to automatically learn feature representations as well as to perform the final classification [30], [31], [32], [33].”
Object Detection in 20 Years: A Survey (2019, background): “An alternative improvement is to design new loss functions [23, 169, 170], by reshaping the standard cross entropy loss so that it will put more focus on hard, misclassified examples [23].”
Traffic-Sign Detection and Classification in the Wild (2016, methodology): “These approaches include using a committee of CNNs [4], multi-scale CNNs [22] and CNNs with a hinge loss function [14], the latter achieving a precision rate of 99.”