arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2009.04724cs.CV
收藏

基于属性引导和纯视觉注意对齐的Few-Shot识别

Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition

Zhejiang University（浙江大学）；Westlake University（西湖大学）

Siteng Huang, Min Zhang, Yachen Kang, Donglin Wang

备注：
An expanded version of the same-name paper accepted by AAAI-2021
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

Few-Shot识别的目的是识别每个类别中具有有限数量的标记示例的新类别。为了鼓励从补充的角度学习，最近的方法已经将辅助语义模态引入到有效的度量学习框架中，该框架旨在学习训练样本（支持集）和测试样本（查询集）之间的特征相似性。然而，这些方法只增加了可用语义的样本的表示，而忽略了查询集，这失去了改进的潜力，并可能导致模态组合和纯视觉表示之间的转变。在本文中，我们设计了一个属性引导的注意力模块（AGAM），以利用人类注释的属性，并学习更多的判别特征。该即插即用模块使视觉内容和相应的属性能够集中在支持集的重要通道和区域上。对于只有视觉信息而没有属性信息的查询集，也实现了特征选择。因此，来自两个集合的表示以细粒度的方式得到改进。此外，提出了一种注意力对齐机制，将知识从属性的指导下提取到无属性样本的纯视觉分支。大量的实验和分析表明，我们提出的模块可以显着改善简单的基于度量的方法，以实现最先进的性能在不同的数据集和设置。

英文摘要：

The purpose of few-shot recognition is to recognize novel categories with a limited number of labeled examples in each class. To encourage learning from a supplementary view, recent approaches have introduced auxiliary semantic modalities into effective metric-learning frameworks that aim to learn a feature similarity between training samples (support set) and test samples (query set). However, these approaches only augment the representations of samples with available semantics while ignoring the query set, which loses the potential for the improvement and may lead to a shift between the modalities combination and the pure-visual representation. In this paper, we devise an attributes-guided attention module (AGAM) to utilize human-annotated attributes and learn more discriminative features. This plug-and-play module enables visual contents and corresponding attributes to collectively focus on important channels and regions for the support set. And the feature selection is also achieved for query set with only visual information while the attributes are not available. Therefore, representations from both sets are improved in a fine-grained manner. Moreover, an attention alignment mechanism is proposed to distill knowledge from the guidance of attributes to the pure-visual branch for samples without attributes. Extensive experiments and analysis show that our proposed module can significantly improve simple metric-based approaches to achieve state-of-the-art performance on different datasets and settings.

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。

↑