63 results about "Misclassification error" patented technology

The invention belongs to the field of image recognition, and specifically relates to an adversarial sample generation method, system and device for outlier removal methods, aiming to solve the problem that the adversarial samples used in the existing deep learning-based classification model training cannot The method of removing outliers makes image classification errors, resulting in the problem of poor robustness and low accuracy of the trained classification model. The present invention includes: obtaining a training data set with a class label, inputting three-dimensional point cloud data into a classification model and calculating a classification loss, respectively calculating the gradient of the classification loss on the three-dimensional point cloud data and the three-dimensional point cloud data on removing outliers The gradient of the two gradients is multiplied by the scaling factor to generate fusion perturbation, and the fusion perturbation is applied to the three-dimensional point cloud data to iteratively generate adversarial samples. The adversarial samples generated by the invention can still cause image classification errors under the condition of removing outliers, which improves the robustness and classification accuracy of the trained model.