Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
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 embed...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2210.06120 |