20 papers with code • 5 benchmarks • 4 datasets
Traffic sign recognition is the task of recognising traffic signs in an image or video.
Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand.
This paper proposes a new approach to detecting neural Trojans on Deep Neural Networks during inference.
For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models.
Also, the issue of late convergence in a Simple black-box attack (SimBA) is addressed by minimizing the loss of the most confused class which is the incorrect class predicted by the model with the highest probability, instead of trying to maximize the loss of the correct class.
Such training data is obtained by embedding synthetic images of signs in the real photos.
Second, we find that compositional deep networks, which have part-based representations that lead to innate robustness to natural occlusion, are robust to patch attacks on PASCAL3D+ and the German Traffic Sign Recognition Benchmark, without adversarial training.
In this paper, an efficient solution to enhance road signs detection, including Arabic context, performance based on color segmentation, Randomized Hough Transform and the combination of Zernike moments and Haralick features has been made.
Several techniques have been proposed to address this problem; one of which is RISE, which explains a classification result by a heatmap, called a saliency map, which explains the significance of each pixel.
We review three recently-proposed classifier quality metrics and consider their suitability for large-scale classification challenges such as applying convolutional neural networks to the 1000-class ImageNet dataset.