Evaluating the Reliability of CNN Models on Classifying Traffic and Road Signs using LIME
Abstract
The objective of this investigation is to evaluate and contrast the effectiveness of four state-of-the-art pre-trained models, ResNet-34, VGG-19, DenseNet-121, and Inception V3, in classifying traffic and road signs with the utilization of the GTSRB public dataset. The study focuses on evaluating the accuracy of these models' predictions as well as their ability to employ appropriate features for image categorization. To gain insights into the strengths and limitations of the model's predictions, the study employs the local interpretable model-agnostic explanations (LIME) framework. The findings of this experiment indicate that LIME is a crucial tool for improving the interpretability and dependability of machine learning models for image identification, regardless of the models achieving an f1 score of 0.99 on classifying traffic and road signs. The conclusion of this study has important ramifications for how these models are used in practice, as it is crucial to ensure that model predictions are founded on the pertinent image features.
Keywords
Cite
@article{arxiv.2309.05747,
title = {Evaluating the Reliability of CNN Models on Classifying Traffic and Road Signs using LIME},
author = {Md. Atiqur Rahman and Ahmed Saad Tanim and Sanjid Islam and Fahim Pranto and G. M. Shahariar and Md. Tanvir Rouf Shawon},
journal= {arXiv preprint arXiv:2309.05747},
year = {2023}
}
Comments
Accepted for publication in the 2nd International Conference on Big Data, IoT and Machine Learning (BIM 2023), 16 pages, 8 figures