Robustness of Neural Decision Trees to noise in input data for image classification tasks
Loading...
Date
2025
Authors
Mokryi, Mykhailo
Shvai, Nadiia
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Neural networks, particularly convolutional neural networks (CNNs), have demonstrated high effectiveness in image classification tasks. However, they are known to be vulnerable to input data perturbations and have weak interpretability due to their black-box nature. In contrast, traditional decision trees (DTs) provide transparent decision-making processes, but are limited to low-dimensional or tabular data, restricting their field of application in computer vision tasks such as image classification. To address this gap, a hybrid architecture known as Neural Decision Trees (NDTs) has emerged, combining strong generalization and learning capabilities of neural networks, with transparent hierarchical inference and interpretability of DTs. The article investigates the robustness of NDTs to noise in input data for image classification tasks. Despite the extensive studies covering the robustness of both CNNs and traditional DTs against various forms of input perturbations, the robustness of NDT models remains a largely underexplored area. This study provides two robust training methods to improve robustness: constant noise learning and incremental noise learning, originally developed for CNNs, but which can be effectively applied to NDT-based architectures and significantly improve the robustness to noisy images for models. These methods involve adding perturbed samples via a Gaussian blur during the training stage. The noisy test set consists of images perturbed
by a Gaussian blur and is used to evaluate the robustness performance. A series of experiments were conducted on the CIFAR-10 dataset using the original training baseline and robust training methods. The results demonstrate that constant and incremental noise learning significantly improve the robustness of all tested NDT models to noisy images compared to their original training performance. While the ResNet18 baseline model demonstrates higher overall performance, the NDT models show comparable robustness improvements using the proposed robust training strategies. Constant noise learning offered an adjustable trade-off between performance on clean and noisy images, while incremental noise learning provided a more stable training process. The first method is considered preferable due to the simplicity of implementation. This study empirically confirms that NDT models can effectively use methods adapted from CNNs to improve their robustness against perturbations in input data. An NDT framework was developed to conduct
training and validation using a standardized shared pipeline. It is available via the link: github.com/ MikhailoMokryy/NDTFramework.
Description
У роботі досліджується стійкість моделей нейронних дерев рішень, які об’єднують архітектуру нейронних мереж і дерев рішень, до шуму у вхідних даних для класифікації зображень. Було запропоновано використати два методи навчання для підвищення стійкості моделей, які початково використовувалися в згорткових нейронних мережах. Зашумлення зображень з набору даних CIFAR-10 відбувається за допомогою методу гаусівського розмиття. Було розглянуто вплив методів підвищення стійкості на моделей нейронних дерев рішень і показано, що стійкість моделей до шуму у вхідних даних значно покращується.
Keywords
Neural Decision Trees, machine learning, robustness, image perturbations, image classification, computer vision, convolutional neural networks, article, нейронні дерева рішень, машинне навчання, стійкість, збурення зображень, класифікація зображень, комп’ютерний зір, згорткові нейронні мережі
Citation
111