https://scholars.lib.ntu.edu.tw/handle/123456789/607369
標題: | Joint feature disentanglement and hallucination for few-shot image classification | 作者: | Lin C.-C Chu H.-L YU-CHIANG WANG CHIN-LAUNG LEI |
關鍵字: | Data hallucination;Feature disentanglement;Few-shot learning (FSL);Image classification;Classification (of information);Disjoint sets;Few-shot learning;Images classification;Learning approach;Learning tasks;Novel concept;Training data;Training sample | 公開日期: | 2021 | 卷: | 30 | 起(迄)頁: | 9245-9258 | 來源出版物: | IEEE Transactions on Image Processing | 摘要: | — Few-shot learning (FSL) refers to the learning task that generalizes from base to novel concepts with only few examples observed during training. One intuitive FSL approach is to hallucinate additional training samples for novel categories. While this is typically done by learning from a disjoint set of base categories with sufficient amount of training data, most existing works did not fully exploit the intra-class information from base categories, and thus there is no guarantee that the hallucinated data would represent the class of interest accordingly. In this paper, we propose Feature Disentanglement and Hallucination Network (FDH-Net), which jointly performs feature disentanglement and hallucination for FSL purposes. More specifically, our FDH-Net is able to disentangle input visual data into class-specific and appearance-specific features. With both data recovery and classification constraints, hallucination of image features for novel categories using appearance information extracted from base categories can be achieved. We perform extensive experiments on two fine-grained datasets (CUB and FLO) and two coarse-grained ones (mini-ImageNet and CIFAR-100). The results confirm that our framework performs favorably against state-of-the-art metric-learning and hallucination-based FSL models. ? 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118679441&doi=10.1109%2fTIP.2021.3124322&partnerID=40&md5=84ddf8d6fe68725a9cfe66d7cb9c73f5 https://scholars.lib.ntu.edu.tw/handle/123456789/607369 |
ISSN: | 10577149 | DOI: | 10.1109/TIP.2021.3124322 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。