• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Artificial Neural Networks >Spatial Attention Network for Few-Shot Learning
【24h】

Spatial Attention Network for Few-Shot Learning

机译：少关注学习的空间注意网络

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Metric learning is one of the feasible approaches to few-shot learning. However, most metric learning methods encode images through CNN directly, without considering image contents. The general CNN features may lead to hard discrimination among distinct classes. Based on observation that feature maps correspond to image regions, we assume that image regions relevant to target objects should be salient in image features. To this end, we propose an effective framework, called Spatial Attention Network (SAN), to exploit spatial context of images. SAN produces attention weights on clustered regional features indicating the contributions of different regions to classification, and takes weighted sum of regional features as discriminative features. Thus, SAN highlights important contents by giving them large weights. Once trained, SAN compares unlabeled data with class prototypes of few labeled data in nearest-neighbor manner and identifies classes of unlabeled data. We evaluate our approach on three disparate datasets: miniImageNet, Caltech-UCSD Birds and miniDogsNet. Experimental results show that when compared with state-of-the-art models, SAN achieves competitive accuracy in miniImageNet and Caltech-UCSD Birds, and it improves 5-shot accuracy in miniDogsNet by a large margin.
机译：公制学习是少拍学习的可行方法之一。但是，大多数度量学习方法都直接通过CNN编码图像，而不考虑图像内容。 CNN的一般功能可能会导致不同类别之间的严格区分。基于特征图对应于图像区域的观察，我们假设与目标对象相关的图像区域在图像特征中应该是显着的。为此，我们提出了一个有效的框架，称为空间注意网络（SAN），以利用图像的空间环境。 SAN对聚类的区域特征产生注意权重，指示不同区域对分类的贡献，并将区域特征的加权总和作为判别特征。因此，SAN通过赋予重要的权重来突出显示重要的内容。经过培训后，SAN会以最近邻居的方式将未标记的数据与少量已标记数据的类原型进行比较，并识别未标记数据的类。我们在三个不同的数据集上评估了我们的方法：miniImageNet，Caltech-UCSD Birds和miniDogsNet。实验结果表明，与最先进的模型相比，SAN在miniImageNet和Caltech-UCSD Birds中具有竞争性的准确性，并且在miniDogsNet中大大提高了5次射击的准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号