期刊
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
卷 -, 期 -, 页码 2525-2528出版社
IEEE
DOI: 10.1109/ICASSP43922.2022.9747827
关键词
Novel class discovery; dependence measure; open set recognition
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据