Classifier and Exemplar Synthesis for Zero-Shot Learning

TL;DR

This paper introduces two novel zero-shot learning frameworks that synthesize classifiers and exemplars for unseen classes, improving performance across multiple visual recognition benchmarks.

Contribution

It proposes manifold embedding-based classifier synthesis and exemplar synthesis methods, advancing zero-shot learning by enabling effective handling of unseen classes.

Findings

Superior performance on five benchmark datasets

Effective synthesis of classifiers and exemplars

Insights into semantic representations and metrics in ZSL

Abstract

Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as learning manifold embeddings from graphs composed of object classes, leading to a flexible approach that synthesizes "classifiers" for the unseen classes. Then, we define an auxiliary task of synthesizing "exemplars" for the unseen classes to be used as an automatic denoising mechanism for any existing ZSL approaches or as an effective ZSL model by itself. On five visual recognition benchmark datasets, we demonstrate the superior performances of our proposed frameworks in various scenarios of both conventional and generalized ZSL. Finally, we provide valuable insights through a series of empirical analyses, among which are a comparison of semantic representations on the full ImageNet benchmark as well as a comparison of metrics used in generalized ZSL. Our code and data are publicly available at https://github.com/pujols/Zero-shot-learning-journal