Discriminative Embedding Autoencoder With a Regressor Feedback for Zero-Shot Learning

Shi, Ying; Wei, Wei

doi:10.1109/access.2020.2964613

Cited by 5 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shi and Wei [143] projected visual features into a discriminative embedding space and constructed an autoen- Fig. 14: A general view demonstrating the proposed QFSL framework (adapted from [149]).…”

Section: Other Methodsmentioning

confidence: 99%

A Review of Generalized Zero-Shot Learning Methods

Pourpanah¹,

Abdar²,

Luo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of both seen (source) and unseen (target) classes to bridge the gap between both seen and unseen classes. Since its introduction, many GZSL models have been formulated. In this review paper, we present a comprehensive review of GZSL. Firstly, we provide an overview of GZSL including the problems and challenging issues. Then, we introduce a hierarchical categorization of the GZSL methods and discuss the representative methods of each category. In addition, we discuss several research directions for future studies.

show abstract

Section: Other Methodsmentioning

confidence: 99%

A Review of Generalized Zero-Shot Learning Methods

Pourpanah¹,

Abdar²,

Luo³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Levy et al (2017) to Common Space. The first direction "Visual to Semantic Embedding" aims to learn a mapping from the visual space to the semantic space either using linear function (Kodirov et al 2017;Shi and Wei 2020) or by deep neural network regression (Annadani and Biswas 2018). Meanwhile, the second direction "Semantic to Visual Embedding" tries to learn a mapping from the semantic space to the visual space (Zhang et al 2020a;Liu et al 2020;Zhang et al 2020b).…”

Section: Related Workmentioning

confidence: 99%

Enhancing Semantic Correlation between Instances and Relations for Zero-Shot Relation Extraction

Tran

Ouchi

Shindo

et al. 2023

Journal of Natural Language Processing

View full text Add to dashboard Cite

Zero-shot relation extraction aims to recognize (new) unseen relations that cannot be observed during training. Due to this point, recognizing unseen relations with no corresponding labeled training instances is a challenging task. Recognizing an unseen relation between two entities in an input instance at the testing time, a model needs to grasp the semantic relationship between the instance and all unseen relations to make a prediction. This study argues that enhancing the semantic correlation between instances and relations is key to effectively solving the zero-shot relation extraction task. A new model entirely devoted to this goal through three main aspects was proposed: learning effective relation representation, designing purposeful mini-batches, and binding two-way semantic consistency. Experimental results on two benchmark datasets demonstrate that our approach significantly improves task performance and achieves state-of-the-art results. Our source code and data are publicly available.

show abstract

“…By constructing a discriminative latent attribute space, Chen et al [29] proposed a discriminative latent attribute autoencoder for zero-shot learning, where the attribute autoencoder is used as a constraint to alleviate the domain shift problem. In order to learn discriminative embedding features, Shi and Wei [30] proposed a discriminative embedding autoencoder for zero-shot learning. The encoder learns a projection function from the visual space to the discriminative embedding space, and then the decoder projects the embedding features back to the visual space.…”

Section: B Semantic Autoencodersmentioning

confidence: 99%

A Distance-Constrained Semantic Autoencoder for Zero-Shot Remote Sensing Scene Classification

Wang¹,

Peng²,

Baets³

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Zero-shot remote sensing scene classification refers to the classification of new images from unseen scene classes and has become a topic of growing interest in the field of remote sensing. Semantic autoencoders are one of the mainstream zeroshot learning methods. However, such autoencoders may not be discriminative enough for remote sensing scene images due to the high within-class diversity and between-class similarity. To address this issue, we propose a distance-constrained semantic autoencoder (DSAE) to deal with zero-shot remote sensing scene classification. More specifically, we learn a semantic autoencoder for seen scene classes, which allows to align the visual space and the semantic space. In order to improve the discriminative ability of this semantic autoencoder, we impose a discriminative distance metric constraint, aiming to minimize the Euclidean distances between the encoded vectors of samples of the same class and maximize the Euclidean distances between the encoded vectors of samples of different classes. Additionally, we learn a semantic autoencoder for unseen scene classes, aiming to alleviate the domain shift problem. Extensive experiments on three benchmark remote sensing scene datasets demonstrate the superiority of the proposed method over state-of-the-art methods.

show abstract

Discriminative Embedding Autoencoder With a Regressor Feedback for Zero-Shot Learning

Cited by 5 publications

References 44 publications

A Review of Generalized Zero-Shot Learning Methods

A Review of Generalized Zero-Shot Learning Methods

Enhancing Semantic Correlation between Instances and Relations for Zero-Shot Relation Extraction

A Distance-Constrained Semantic Autoencoder for Zero-Shot Remote Sensing Scene Classification

Contact Info

Product

Resources

About