Holistically associated transductive zero-shot learning

With the explosive growth of visual media categories, zero-shot learning (ZSL) aims to transfer the knowledge obtained from the seen classes to the unseen classes for recognizing novel instances. However, there is a domain gap between the seen and the unseen classes, and simply matching the unseen i...

Full description

Saved in:
Bibliographic Details
Main Authors: XU, Yangyang, XU, Xuemiao, HAN, Guoqiang, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7862
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8865
record_format dspace
spelling sg-smu-ink.sis_research-88652023-06-15T09:00:05Z Holistically associated transductive zero-shot learning XU, Yangyang XU, Xuemiao HAN, Guoqiang HE, Shengfeng With the explosive growth of visual media categories, zero-shot learning (ZSL) aims to transfer the knowledge obtained from the seen classes to the unseen classes for recognizing novel instances. However, there is a domain gap between the seen and the unseen classes, and simply matching the unseen instances using nearest neighbor searching in the embedding space cannot bridge this gap effectively. In this article, we propose a holistically associated model to overcome this obstacle. In particular, the proposed model is designed to combat two fundamental problems of ZSL: 1) the representation learning and 2) label assignment of the unseen classes. The first problem is addressed by proposing an affinity propagation network, which considers holistic pairwise connections of all classes for producing exemplar features of the unseen samples. We cope with the second issue by proposing a progressive clustering module. It iteratively refines unseen clusters so that holistic unseen instance features can be used for a reliable classwise label assignment. Thanks to the precise exemplar features and classwise label assignment, our model eliminates the domain gap effectively. We extensively evaluate the proposed model on five human action and image data sets, i.e., Olympics Sports, HMDB51, UCF101, Animals with Attributes 2, and SUN. The experimental results show that the proposed model outperforms state-of-the-art methods on these substantially different data sets. 2022-06-01T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/7862 info:doi/10.1109/TCDS.2021.3049274 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Visualization Semantics Artificial neural networks Predictive models Training Pairwise error probability Loss measurement Affinity matrix class association instance association zero-shot learning (ZSL) Information Security
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Visualization
Semantics
Artificial neural networks
Predictive models
Training
Pairwise error probability
Loss measurement
Affinity matrix
class association
instance association
zero-shot learning (ZSL)
Information Security
spellingShingle Visualization
Semantics
Artificial neural networks
Predictive models
Training
Pairwise error probability
Loss measurement
Affinity matrix
class association
instance association
zero-shot learning (ZSL)
Information Security
XU, Yangyang
XU, Xuemiao
HAN, Guoqiang
HE, Shengfeng
Holistically associated transductive zero-shot learning
description With the explosive growth of visual media categories, zero-shot learning (ZSL) aims to transfer the knowledge obtained from the seen classes to the unseen classes for recognizing novel instances. However, there is a domain gap between the seen and the unseen classes, and simply matching the unseen instances using nearest neighbor searching in the embedding space cannot bridge this gap effectively. In this article, we propose a holistically associated model to overcome this obstacle. In particular, the proposed model is designed to combat two fundamental problems of ZSL: 1) the representation learning and 2) label assignment of the unseen classes. The first problem is addressed by proposing an affinity propagation network, which considers holistic pairwise connections of all classes for producing exemplar features of the unseen samples. We cope with the second issue by proposing a progressive clustering module. It iteratively refines unseen clusters so that holistic unseen instance features can be used for a reliable classwise label assignment. Thanks to the precise exemplar features and classwise label assignment, our model eliminates the domain gap effectively. We extensively evaluate the proposed model on five human action and image data sets, i.e., Olympics Sports, HMDB51, UCF101, Animals with Attributes 2, and SUN. The experimental results show that the proposed model outperforms state-of-the-art methods on these substantially different data sets.
format text
author XU, Yangyang
XU, Xuemiao
HAN, Guoqiang
HE, Shengfeng
author_facet XU, Yangyang
XU, Xuemiao
HAN, Guoqiang
HE, Shengfeng
author_sort XU, Yangyang
title Holistically associated transductive zero-shot learning
title_short Holistically associated transductive zero-shot learning
title_full Holistically associated transductive zero-shot learning
title_fullStr Holistically associated transductive zero-shot learning
title_full_unstemmed Holistically associated transductive zero-shot learning
title_sort holistically associated transductive zero-shot learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/7862
_version_ 1770576571464155136