.png){kind=icon}
返回
A plug-in attribute corr ection module for generalized zero-shot learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2020.107767.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
While Zero Shot Learning models can recognize new classes without training examples, they often fails to incorporate both seen and unseen classes together at the test time, which is known as the Generalized Zero-shot Learning (GZSL) problem. This paper identifies a bottleneck issue when attributes are not well-defined, reliable, inaccurate in quantitative representations, or suffering from the visual-semantic discrepancy. We propose a Generic Plug-in Attribute Correction (GPAC) module which can effectively accommodate conventional ZSL in GZSL tasks. Different from existing embedding-based approaches which often lose the favor of transparency in attributes, our key challenge is to fully preserve the original meaning of the attributes and make it complementary and interpretable to upgrade existing ZSL models. To this end, we propose a novel nonnegative constraint with iterative Stochastic Gradient Descent toolbox to effectively fit our GPAC module into previous ZSL models. Extensive experiments on five popular datasets show that our method can effectively correct attributes and make conventional ZSL can achieve state-ofthe-art performance on GZSL tasks. It is also a good practice for future models when incorporating prior human knowledge. (c) 2020 Elsevier Ltd. All rights reserved.
Keyword:
Generalized zero shot learning (GZSL)
Attribute correction
Orthogonal constraint
pluggable module
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Modality-specific and shared generative adversarial network for cross-modal retrieval用于跨模态检索的特定模态和共享生成对抗网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Transcatheter occlusion of the persistently patent ductus arteriosus. Forty-month follow-up and prevalence of residual shunting.CirculationOAAI
CirculationIF0
OAAI分享收藏Deep transductive network for generalized zero shot learning用于广义零射击学习的深度转导网络PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
Guided CNN for generalized zero-shot and open-set recognition using visual and semantic prototypes使用视觉和语义原型进行广义零拍和开放集识别的引导CNNPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏 没有更多内容
没有更多内容