人工智能
计算机科学
班级(哲学)
机器学习
相似性(几何)
二元关系
关系(数据库)
二元分类
无监督学习
模式识别(心理学)
图像(数学)
数据挖掘
数学
支持向量机
离散数学
作者
Hongguang Zhang,Piotr Koniusz,Songlei Jian,Hongdong Li,Philip H. S. Torr
标识
DOI:10.1109/cvpr46437.2021.00931
摘要
The majority of existing few-shot learning methods describe image relations with binary labels. However, such binary relations are insufficient to teach the network complicated real-world relations, due to the lack of decision smoothness. Furthermore, current few-shot learning models capture only the similarity via relation labels, but they are not exposed to class concepts associated with objects, which is likely detrimental to the classification performance due to underutilization of the available class labels. For instance, children learn the concept of tiger from a few of actual examples as well as from comparisons of tiger to other animals. Thus, we hypothesize that both similarity and class concept learning must be occurring simultaneously. With these observations at hand, we study the fundamental problem of simplistic class modeling in current few-shot learning methods. We rethink the relations between class concepts, and propose a novel Absolute-relative Learning paradigm to fully take advantage of label information to refine the image an relation representations in both supervised and unsupervised scenarios. Our proposed paradigm improves the performance of several state-of-the-art models on publicly available datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI