A Joint Representation Learning and Feature Modeling Approach for One-class Recognition
A Joint Representation Learning and Feature Modeling Approach for One-class Recognition
复制标题
DOI：
10.1109/icpr48806.2021.9412390
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Pramuditha Perera;Vishal M. Patel
中科院分区：
文献类型：
--
作者：
Pramuditha Perera;Vishal M. Patel
单类识别传统上是作为一个表示学习问题或特征建模问题。在这项工作中，我们认为，这两种方法都有自己的局限性，可以通过结合两者得到更有效的解决方案。所提出的方法是基于生成框架和一类分类方法的组合。首先，我们使用具有生成框架的单类数据来学习生成特征。我们用相应的重建误差来增强学习的特征，以获得增强的特征。然后，我们定性地确定一个合适的特征分布，减少所选分类器空间中的冗余。最后，我们使用对抗框架强制增强特征采用这种分布的形式。我们测试了所提出的方法的有效性上三个一类分类任务，并获得国家的最先进的结果。
One-class recognition is traditionally approached either as a representation learning problem or a feature modelling problem. In this work, we argue that both of these approaches have their own limitations; and a more effective solution can be obtained by combining the two. The proposed approach is based on the combination of a generative framework and a one-class classification method. First, we learn generative features using the one-class data with a generative framework. We augment the learned features with the corresponding reconstruction errors to obtain augmented features. Then, we qualitatively identify a suitable feature distribution that reduces the redundancy in the chosen classifier space. Finally, we force the augmented features to take the form of this distribution using an adversarial framework. We test the effectiveness of the proposed method on three one-class classification tasks and obtain state-of-the-art results.