A Simple Exponential Family Framework for Zero-Shot Learning
This work addresses the problem of predicting unseen classes in machine learning, which is incremental as it builds on existing generative and attribute-based methods for zero-shot learning.
The paper tackles zero-shot learning by proposing a generative framework that models class-conditional distributions as exponential family distributions, enabling prediction of unseen classes using class attributes. It demonstrates efficacy through experiments on benchmark datasets, with results showing competitive performance, though specific numbers are not provided in the abstract.
We present a simple generative framework for learning to predict previously unseen classes, based on estimating class-attribute-gated class-conditional distributions. We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are defined as functions of the respective observed class attributes. These functions can be learned using only the seen class data and can be used to predict the parameters of the class-conditional distribution of each unseen class. Unlike most existing methods for zero-shot learning that represent classes as fixed embeddings in some vector space, our generative model naturally represents each class as a probability distribution. It is simple to implement and also allows leveraging additional unlabeled data from unseen classes to improve the estimates of their class-conditional distributions using transductive/semi-supervised learning. Moreover, it extends seamlessly to few-shot learning by easily updating these distributions when provided with a small number of additional labelled examples from unseen classes. Through a comprehensive set of experiments on several benchmark data sets, we demonstrate the efficacy of our framework.