Abstract
Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embedding and a Gaussian Process (GP) regression model that predicts latent feature prototypes of unseen classes. A calibrated classifier is then constructed for ZSL and Generalized ZSL tasks. Our Neural Network model is trained efficiently with a simple training strategy that mitigates the impact of class-imbalanced training data. The model has an average training time of 5 minutes and can achieve state-of-the-art (SOTA) performance on imbalanced ZSL benchmark datasets like AWA2, AWA1 and APY, while having relatively good performance on the SUN and CUB datasets.
| Original language | English |
|---|---|
| Title of host publication | 2022 26th International Conference on Pattern Recognition, ICPR 2022 |
| Editors | Michael Jenkin, Henrik I. Christensen, Cheng-Lin Liu |
| Place of Publication | Piscataway NJ USA |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 2078-2085 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781665490627 |
| ISBN (Print) | 9781665490634 |
| DOIs | |
| Publication status | Published - 2022 |
| Externally published | Yes |
| Event | International Conference on Pattern Recognition 2022 - Montreal, Canada Duration: 21 Aug 2022 → 25 Aug 2022 Conference number: 26th https://ieeexplore.ieee.org/xpl/conhome/9956007/proceeding (Proceedings) https://iapr.org/archives/icpr2022/index.html (Website) |
Publication series
| Name | Proceedings - International Conference on Pattern Recognition |
|---|---|
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Volume | 2022-August |
| ISSN (Print) | 1051-4651 |
| ISSN (Electronic) | 2831-7475 |
Conference
| Conference | International Conference on Pattern Recognition 2022 |
|---|---|
| Abbreviated title | ICPR 2022 |
| Country/Territory | Canada |
| City | Montreal |
| Period | 21/08/22 → 25/08/22 |
| Internet address |