Multi-Class Novelty Detection Using Mix-Up Technique

2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV)(2020)

引用 7|浏览4
暂无评分
摘要
Multi-class novelty detection is increasingly becoming an important area of research due to the continuous increase in the number of object categories. It tries to answer the pertinent question: given a test sample, should we even try to classify it? We propose a novel solution using the concept of mix-up technique for novelty detection, termed as Segregation Network. During training, a pair of examples are selected from the training data and an interpolated data point using their convex combination is constructed. We develop a suitable loss function to train our model to predict its constituent classes. During testing, each input query is combined with the known class prototypes to generate mixed samples which are then passed through the trained network. Our model which is trained to reveal the constituent classes can then be used to determine whether the sample is novel or not. The intuition is that if a query comes from a known class and is mixed with the set of known class prototypes, then the prediction of the trained model for the correct class should be high. In contrast, for a query from a novel class, the predictions for all the known classes should be low. The proposed model is trained using only the available known class data and does not need access to any auxiliary dataset or attributes. Extensive experiments on two benchmark datasets, namely Caltech 256 and Stanford Dogs and comparisons with the state-of-the-art algorithms justifies the usefulness of our approach.
更多
查看译文
关键词
multiclass novelty detection,mix-up technique,test sample,training data,interpolated data point,constituent classes,class prototypes,trained network,trained model,class data,segregation network,convex combination,loss function
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要