HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning
Zero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or predicting classes (labels) that are not involved in the training set (unseen classes). A well-known problem in Deep Learning (DL) is the requirement for large amount of training data. Zero-Shot learnin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/8/6/171 |
| _version_ | 1797485822402887680 |
|---|---|
| author | Fadi Al Machot Mohib Ullah Habib Ullah |
| author_facet | Fadi Al Machot Mohib Ullah Habib Ullah |
| author_sort | Fadi Al Machot |
| collection | DOAJ |
| description | Zero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or predicting classes (labels) that are not involved in the training set (unseen classes). A well-known problem in Deep Learning (DL) is the requirement for large amount of training data. Zero-Shot learning is a straightforward approach that can be applied to overcome this problem. We propose a Hybrid Feature Model (HFM) based on conditional autoencoders for training a classical machine learning model on pseudo training data generated by two conditional autoencoders (given the semantic space as a condition): (a) the first autoencoder is trained with the visual space concatenated with the semantic space and (b) the second autoencoder is trained with the visual space as an input. Then, the decoders of both autoencoders are fed by the test data of the unseen classes to generate pseudo training data. To classify the unseen classes, the pseudo training data are combined to train a support vector machine. Tests on four different benchmark datasets show that the proposed method shows promising results compared to the current state-of-the-art when it comes to settings for both standard Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL). |
| first_indexed | 2024-03-09T23:24:23Z |
| format | Article |
| id | doaj.art-5868d475003a4c49be9eadfaf9b556f1 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-09T23:24:23Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-5868d475003a4c49be9eadfaf9b556f12023-11-23T17:20:41ZengMDPI AGJournal of Imaging2313-433X2022-06-018617110.3390/jimaging8060171HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot LearningFadi Al Machot0Mohib Ullah1Habib Ullah2Faculty of Science and Technology, Norwegian University of Life Science (NMBU), 1430 Ås, NorwayDepartment of Computer Science, Norwegian University of Science and Technology, 2819 Gjøvik, NorwayFaculty of Science and Technology, Norwegian University of Life Science (NMBU), 1430 Ås, NorwayZero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or predicting classes (labels) that are not involved in the training set (unseen classes). A well-known problem in Deep Learning (DL) is the requirement for large amount of training data. Zero-Shot learning is a straightforward approach that can be applied to overcome this problem. We propose a Hybrid Feature Model (HFM) based on conditional autoencoders for training a classical machine learning model on pseudo training data generated by two conditional autoencoders (given the semantic space as a condition): (a) the first autoencoder is trained with the visual space concatenated with the semantic space and (b) the second autoencoder is trained with the visual space as an input. Then, the decoders of both autoencoders are fed by the test data of the unseen classes to generate pseudo training data. To classify the unseen classes, the pseudo training data are combined to train a support vector machine. Tests on four different benchmark datasets show that the proposed method shows promising results compared to the current state-of-the-art when it comes to settings for both standard Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL).https://www.mdpi.com/2313-433X/8/6/171Zero-Shot Learning (ZSL)semantic spaceconditional autoencodersgenerative modelscomputer vision |
| spellingShingle | Fadi Al Machot Mohib Ullah Habib Ullah HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning Journal of Imaging Zero-Shot Learning (ZSL) semantic space conditional autoencoders generative models computer vision |
| title | HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning |
| title_full | HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning |
| title_fullStr | HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning |
| title_full_unstemmed | HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning |
| title_short | HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning |
| title_sort | hfm a hybrid feature model based on conditional auto encoders for zero shot learning |
| topic | Zero-Shot Learning (ZSL) semantic space conditional autoencoders generative models computer vision |
| url | https://www.mdpi.com/2313-433X/8/6/171 |
| work_keys_str_mv | AT fadialmachot hfmahybridfeaturemodelbasedonconditionalautoencodersforzeroshotlearning AT mohibullah hfmahybridfeaturemodelbasedonconditionalautoencodersforzeroshotlearning AT habibullah hfmahybridfeaturemodelbasedonconditionalautoencodersforzeroshotlearning |