Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data.
Ranked #19 on Domain Generalization on ImageNet-C
While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy.
Deep neural networks that yield human interpretable decisions by architectural design have lately become an increasingly popular alternative to post hoc interpretation of traditional black-box models.
For modelling we propose a novel semi-supervised algorithm called Fusion Hidden Markov Model (FHMM) which is more robust to noise, requires comparatively less training time, and utilizes the benefits of ensemble learning to better model temporal relationships in data.