Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance
This addresses the need for reliable anomaly detection in deep learning systems for safety-critical domains like autonomous vehicles, but it is incremental as it builds on existing reconstruction-based methods.
The paper tackled the problem of detecting out-of-distribution samples in safety-critical applications by proposing a method that incorporates Mahalanobis distance in latent space, which often improves performance over baseline reconstruction-based autoencoders.
There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems. A number of recent papers have proposed methods for detecting anomalous image data that appear different from known inlier data samples, including reconstruction-based autoencoders. Autoencoders optimize the compression of input data to a latent space of a dimensionality smaller than the original input and attempt to accurately reconstruct the input using that compressed representation. Since the latent vector is optimized to capture the salient features from the inlier class only, it is commonly assumed that images of objects from outside of the training class cannot effectively be compressed and reconstructed. Some thus consider reconstruction error as a kind of novelty measure. Here we suggest that reconstruction-based approaches fail to capture particular anomalies that lie far from known inlier samples in latent space but near the latent dimension manifold defined by the parameters of the model. We propose incorporating the Mahalanobis distance in latent space to better capture these out-of-distribution samples and our results show that this method often improves performance over the baseline approach.