An Integral Projection-Based Semantic Autoencoder for Zero-Shot Learning
Zero-shot Learning (ZSL) classification categorizes or predicts classes (labels) that are not included in the training set (unseen classes). Recent works proposed different semantic autoencoder (SAE) models where the encoder embeds a visual feature vector space into the semantic space and the decode...
Main Authors: | William Heyden, Habib Ullah, Muhammad Salman Siddiqui, Fadi Al-Machot |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10213991/ |
Similar Items
-
HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning
by: Fadi Al Machot, et al.
Published: (2022-06-01) -
Zero-shot learning via visual-semantic aligned autoencoder
by: Tianshu Wei, et al.
Published: (2023-06-01) -
A semantic and emotion‐based dual latent variable generation model for a dialogue system
by: Ming Yan, et al.
Published: (2023-06-01) -
EVAE-Net: An Ensemble Variational Autoencoder Deep Learning Network for COVID-19 Classification Based on Chest X-ray Images
by: Daniel Addo, et al.
Published: (2022-10-01) -
Quantitative analysis of latent space in airfoil shape generation using variational autoencoders
by: Kazuo YONEKURA
Published: (2021-10-01)