arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00340cs.CV
收藏

重构引导的元学习用于小样本开集识别

Reconstruction guided Meta-learning for Few Shot Open Set Recognition

Sayak Nag, Dripta S. Raychaudhuri, Sujoy Paul, Amit K. Roy-Chowdhury

AI总结:

针对小样本开集识别中阈值敏感、细粒度分类不准的问题,提出基于样例重构元学习的 ReFOCS,通过学习样本开放性免阈值调优,并在多数据集上超越现有方法。

摘要:

在许多应用中,我们受到只能从极有限数据中学习分类器的限制,即小样本分类。如果还要求识别来自未知类别的样本,即开集分类,任务会变得更具挑战性。在样本极少的情况下为一个类别学习良好的抽象极其困难,尤其是在开集环境下。因此,开集识别在小样本场景中受到的关注很少。然而,它在环境监测等许多应用中是一项关键任务,因为这些应用中每个类别的有标注样本数量有限。现有的小样本开集识别(FSOSR)方法依赖阈值机制,其中一些方法还为开集类别样本考虑均匀概率。然而,这种方法通常并不准确,尤其是在细粒度分类中,并使这些方法对阈值选择高度敏感。为解决这些问题,我们提出了 Reconstructing Exemplar-based Few-shot Open-set ClaSsifier(ReFOCS,基于样例重构的小样本开集分类器)。通过采用一种新颖的基于样例重构的元学习策略,ReFOCS 简化了 FSOSR;它通过学习感知样本的开放性,消除了对精心调节阈值的需求。样例充当类别代表,既可以由训练数据集提供,也可以在特征域中估计。通过在多种数据集上进行测试,我们表明 ReFOCS 优于多种最先进方法。

英文摘要:

In many applications, we are constrained to learn classifiers from very limited data (few-shot classification). The task becomes even more challenging if it is also required to identify samples from unknown categories (open-set classification). Learning a good abstraction for a class with very few samples is extremely difficult, especially under open-set settings. As a result, open-set recognition has received minimal attention in the few-shot setting. However, it is a critical task in many applications like environmental monitoring, where the number of labeled examples for each class is limited. Existing few-shot open-set recognition (FSOSR) methods rely on thresholding schemes, with some considering uniform probability for open-class samples. However, this approach is often inaccurate, especially for fine-grained categorization, and makes them highly sensitive to the choice of a threshold. To address these concerns, we propose Reconstructing Exemplar-based Few-shot Open-set ClaSsifier (ReFOCS). By using a novel exemplar reconstruction-based meta-learning strategy ReFOCS streamlines FSOSR eliminating the need for a carefully tuned threshold by learning to be self-aware of the openness of a sample. The exemplars, act as class representatives and can be either provided in the training dataset or estimated in the feature domain. By testing on a wide variety of datasets, we show ReFOCS to outperform multiple state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑