arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2010.04525cs.CV
收藏

不确定性感知的Few-Shot图像分类

Uncertainty-Aware Few-Shot Image Classification

University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院);Columbia University(哥伦比亚大学)

Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen, Shih-Fu Chang

摘要:

Few-Shot图像分类学习从有限的标记数据中识别新的类别。基于度量学习的方法已经得到了广泛的研究,其中查询样本通过基于其特征相似性从支持集中找到最接近的原型来分类。一个神经网络在计算不同对的相似度时具有不同的不确定性。理解和建模相似性的不确定性,可以促进有限样本的开发在Few-Shot优化。在这项工作中,我们提出了不确定性感知的Few-Shot框架的图像分类的查询支持对的相似性建模的不确定性和执行不确定性感知优化。特别是,我们利用这种不确定性,通过将观察到的相似性转换为概率表示,并将其纳入损失更有效的优化。为了联合考虑查询和支持集中的原型之间的相似性,基于图的模型被用来估计对的不确定性。大量的实验表明,我们提出的方法带来了显着的改进上一个强大的基线,并实现了国家的最先进的性能。

英文摘要:

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set based on their feature similarities. A neural network has different uncertainties on its calculated similarities of different pairs. Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization. In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we exploit such uncertainty by converting observed similarities to probabilistic representations and incorporate them to the loss for more effective optimization. In order to jointly consider the similarities between a query and the prototypes in a support set, a graph-based model is utilized to estimate the uncertainty of the pairs. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.

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。

↑