Uncertainty in AI: Evaluating Deep Neural Networks on Out-of-Distribution Images
It addresses the critical issue of AI model reliability in unusual situations for deployment in safety-critical applications, but it is incremental as it applies existing methods to new data.
This paper tackles the problem of evaluating deep neural networks' performance and uncertainty on out-of-distribution (OOD) and perturbed images, finding that an ensemble method outperformed single models by correctly classifying all OOD images, but ResNet-50 misclassified all perturbed images despite high accuracy on unperturbed ones.
As AI models are increasingly deployed in critical applications, ensuring the consistent performance of models when exposed to unusual situations such as out-of-distribution (OOD) or perturbed data, is important. Therefore, this paper investigates the uncertainty of various deep neural networks, including ResNet-50, VGG16, DenseNet121, AlexNet, and GoogleNet, when dealing with such data. Our approach includes three experiments. First, we used the pretrained models to classify OOD images generated via DALL-E to assess their performance. Second, we built an ensemble from the models' predictions using probabilistic averaging for consensus due to its advantages over plurality or majority voting. The ensemble's uncertainty was quantified using average probabilities, variance, and entropy metrics. Our results showed that while ResNet-50 was the most accurate single model for OOD images, the ensemble performed even better, correctly classifying all images. Third, we tested model robustness by adding perturbations (filters, rotations, etc.) to new epistemic images from DALL-E or real-world captures. ResNet-50 was chosen for this being the best performing model. While it classified 4 out of 5 unperturbed images correctly, it misclassified all of them post-perturbation, indicating a significant vulnerability. These misclassifications, which are clear to human observers, highlight AI models' limitations. Using saliency maps, we identified regions of the images that the model considered important for their decisions.