Journal
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Volume -, Issue -, Pages 2525-2528Publisher
IEEE
DOI: 10.1109/ICASSP43922.2022.9747827
Keywords
Novel class discovery; dependence measure; open set recognition
Ask authors/readers for more resources
This paper investigates the problem of discovering novel classes never encountered in the labeled set, and proposes a dependency measure based on Squared Mutual Information (SMI) to simultaneously learn to classify and cluster the data. Experimental results show competitive performance on CIFAR and Imagenet datasets.
Supervised and semi-supervised algorithms have been designed under a closed-world setting, with the assumption that unlabeled data consists of classes previously seen in labeled training data. However, real world is inherently open set where this assumption is often violated, and thus novel data may be encountered in test data. In this paper, we look at the problem where the model is required to discover novel classes never encountered in the labeled set. We propose a dependency measure based on Squared Mutual Information (SMI) where we simultaneously learn to classify and cluster the data. Our experiments show that our approach is able to achieve competitive performance on CIFAR and Imagenet datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available