OD-test | OD-test : A Less Biased Evaluation of Out-of-Distribution | Machine Learning library

OD-test is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch, Tensorflow applications. OD-test has no bugs, it has no vulnerabilities, it has a Permissive License and it has low support. However OD-test build file is not available. You can download it from GitHub.

The problem of interest is out-of-distribution (OOD) sample detection. In our paper, we present an evaluation framework called OD-test for methods that address OOD sample detection. We show that the traditional evaluation strategy yields overly-optimistic results, hence the need for more reliable evaluation. In this repository, we implement the OD-test for image recognition problems with deep neural networks. You can replicate all the results of our paper here. The OOD detection problem arises in settings where the input of the neural network in a deployed system is not guaranteed to follow a fixed distribution. OOD inputs can lead to unpredictable behaviour in neural network pipelines. For instance, the neural network might be trained to recognize the MNIST digits, but then when deployed, it might encounter a natural image which it has never seen. Counter-intuitively, the trained neural networks often fail silently and make over-confident predictions on previously unseen input. We need to develop methods that detect OOD samples to prevent unpredictable behaviour. Unfortunately, we cannot filter out these problematic instances by thresholding the output probability of the most likely class. In the above image, we show the output of several popular CNNs trained on ImageNet but tested on random benign images that do not belong to ImageNet. The code in this repository allows. I have spent a long time refining this code. The final result is a modularized codebase that is reasonably efficient. I recommend that you take the time to understand the general architecture of the project before making substantial changes. I welcome pull-requests. In particular, if you wish to add a new method to the evaluation or improve a part of the code. You can ask questions in Issues.