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 2108.09666cs.CV
收藏

Few-Shot分类的关系嵌入

Relational Embedding for Few-Shot Classification

Pohang University of Science and Technology (POSTECH)(浦项科技大学)

Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho

摘要:

我们建议解决的问题,Few-Shot分类元学习“观察什么”和“在哪里参加”的关系的角度来看。我们的方法通过自相关表示(SCR)和交叉相关注意力(CCA)利用图像内和图像之间的关系模式。在每个图像中,SCR模块将基本特征映射转换为自相关张量,并学习从张量中提取结构模式。在图像之间,CCA模块计算两个图像表示之间的互相关,并学习在它们之间产生共同关注。我们的关系嵌入网络(RENet)结合了这两个关系模块,以端到端的方式学习关系嵌入。在实验评估中,它在miniImageNet,tieredImageNet,CUB-200-2011和CIFAR-FS四个广泛使用的Few-Shot分类基准上实现了对最先进方法的一致改进。

英文摘要:

We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method leverages relational patterns within and between images via self-correlational representation (SCR) and cross-correlational attention (CCA). Within each image, the SCR module transforms a base feature map into a self-correlation tensor and learns to extract structural patterns from the tensor. Between the images, the CCA module computes cross-correlation between two image representations and learns to produce co-attention between them. Our Relational Embedding Network (RENet) combines the two relational modules to learn relational embedding in an end-to-end manner. In experimental evaluation, it achieves consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmarks of miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS.

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。

↑