CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition

被引：30

作者：

Kozerawski, Jedrzej ^{[1
]}

Turk, Matthew ^{[1
]}

机构：

[1] Univ Calif Santa Barbara, Santa Barbara, CA 93106 USA

来源：

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/CVPR.2018.00363

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This work addresses the novel problem of one-shot one class classification. The goal is to estimate a classification decision boundary for a novel class based on a single image example. Our method exploits transfer learning to model the transformation from a representation of the input, extracted by a Convolutional Neural Network, to a classification decision boundary. We use a deep neural network to learn this transformation from a large labelled dataset of images and their associated class decision boundaries generated from ImageNet, and then apply the learned decision boundary to classify subsequent query images. We tested our approach on several benchmark datasets and significantly outperformed the baseline methods.

引用

页码：3446 / 3455

页数：10