The objective of Open set recognition (OSR) is to learn a classifier that can reject the unknown samples while classifying the known classes accurately. In this paper, we propose a self-supervision method, Detransformation Autoencoder (DTAE), for the OSR problem. This proposed method engages in learning representations that are invariant to the transformations of the input data. Experiments on several standard image datasets indicate that the pre-training process significantly improves the model performance in the OSR tasks. Meanwhile, our proposed self-supervision method achieves significant gains in detecting the unknown class and classifying the known classes. Moreover, our analysis indicates that DTAE can yield representations that contain more target class information and less transformation information than RotNet.
翻译:开放数据集识别(OSR)的目标是学习一个分类器,该分类器可以拒绝未知的样本,同时对已知的类别进行准确分类。在本文中,我们建议针对 OSR 问题采用自我监督方法(Detransformation Autoencoder (DTAE) 。这一拟议方法涉及与输入数据转换不相容的学习表达方式。关于几个标准图像数据集的实验表明,培训前过程大大改进了OSR 任务中的模型性能。 同时,我们提议的自我监督方法在发现未知类别和对已知类别进行分类方面取得了显著成果。此外,我们的分析表明,DTAE 能够产生比 RotNet 包含更多目标类别信息和更少转换信息的表达方式。