Towards Visual Classification Under Class Ambiguity

Abstract

Visual classification under uncertainty is a complex computer vision problem. We present a thorough comparison of several variants of convolutional neural network (CNN) classification techniques in the context of ambiguous image data interpretation. We explore possible improvements in classification accuracy achieved by insertion of prior ambiguity information during the annotation process. This enables us to harness known similarities between individual classes and use them as probability distributions for soft ground-truth labels. We also present an approach based on Bayesian CNNs, offering the possibility of further interpretation of classification results in a problem where the neural network model is often considered as a black box. The presented techniques are verified on a practical spot weld inspection problem.