通过多层级相关性捕捉图像局部语义，提升少样本分类性能。
Multi-Level Correlation Network For Few-Shot Image Classification
- 设计自相关与交叉相关模块，挖掘局部特征语义对应关系。
- 引入模式相关模块，发现基类与新类间的结构相似性。
- 在四个主流数据集上验证有效，适合图像细粒度识别任务。
少样本图像分类（Few-shot Image Classification, FSIC）旨在仅用少量标注图像识别新类别。近期工作虽取得良好效果，尤其基于度量学习的方法通常仅在图像特征层面进行度量。本文认为，仅依赖该层面的度量在仅使用少量图像时可能不足以实现从基类到新类的有效泛化。因此，本文提出多层级相关网络（MLCN），通过有效捕捉图像局部信息来解决此问题。具体地，我们设计自相关模块与交叉相关模块，基于学习到的表示挖掘局部信息的语义对应关系；同时提出模式相关模块，用于捕捉细粒度图像的模式，并发现基类与新类之间的相关结构模式。大量实验与分析表明，所提方法在四个广泛使用的FSIC基准数据集上均表现优异。代码已公开于：https://github.com/Yunkai696/MLCN。
原文摘要 · Abstract (English)
Few-shot image classification(FSIC) aims to recognize novel classes given few labeled images from base classes. Recent works have achieved promising classification performance, especially for metric-learning methods, where a measure at only image feature level is usually used. In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images. Instead, a multi-level descriptor of an image is taken for consideration in this paper. We propose a multi-level correlation network (MLCN) for FSIC to tackle this problem by effectively capturing local information. Concretely, we present the self-correlation module and cross-correlation module to learn the semantic correspondence relation of local information based on learned representations. Moreover, we propose a pattern-correlation module to capture the pattern of fine-grained images and find relevant structural patterns between base classes and novel classes. Extensive experiments and analysis show the effectiveness of our proposed method on four widely-used FSIC benchmarks. The code for our approach is available at: https://github.com/Yunkai696/MLCN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。