论文标题
在开放式识别的自我监督表示学习中的特征解耦
Feature Decoupling in Self-supervised Representation Learning for Open Set Recognition
论文作者
论文摘要
假设在分类过程中可能存在未知类，则开放集识别（OSR）任务旨在将实例分类为已知类别或拒绝其未知类别。在本文中，我们针对OSR问题使用了两阶段的培训策略。在第一阶段，我们引入了一种自我监管的特征解耦方法，该方法从已知类别中找到输入样本的内容特征。具体而言，我们的功能解耦方法学习了一个可以分为内容功能和转换功能的表示形式。在第二阶段，我们用类标签微调内容的特征。然后将微调的内容功能用于OSR问题。此外，我们考虑了一个无监督的OSR方案，我们将在其中从第一阶段学到的内容特征。为了衡量表示质量，我们引入内部内部比率（IIR）。我们的实验结果表明，我们提议的自我监督方法在图像和恶意软件OSR问题上的表现优于其他人。另外，我们的分析表明IIR与OSR性能相关。
Assuming unknown classes could be present during classification, the open set recognition (OSR) task aims to classify an instance into a known class or reject it as unknown. In this paper, we use a two-stage training strategy for the OSR problems. In the first stage, we introduce a self-supervised feature decoupling method that finds the content features of the input samples from the known classes. Specifically, our feature decoupling approach learns a representation that can be split into content features and transformation features. In the second stage, we fine-tune the content features with the class labels. The fine-tuned content features are then used for the OSR problems. Moreover, we consider an unsupervised OSR scenario, where we cluster the content features learned from the first stage. To measure representation quality, we introduce intra-inter ratio (IIR). Our experimental results indicate that our proposed self-supervised approach outperforms others in image and malware OSR problems. Also, our analyses indicate that IIR is correlated with OSR performance.
