# Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification

## TL;DR

This paper introduces a new zero-shot learning framework that combines label attribute information and hierarchical label structures, improving image classification across semantic levels.

## Contribution

It presents two novel methods, lifted zero-shot prediction and a CRF model, integrating label attributes and hierarchies for enhanced zero-shot classification.

## Key findings

- Lifted zero-shot prediction outperforms baseline methods within semantic levels.
- CRF model's probability distribution improves unconstrained hierarchical predictions.
- Benchmark tasks demonstrate the effectiveness of the proposed framework.

## Abstract

Zero-shot learning (ZSL) is one of the most extreme forms of learning from scarce labeled data. It enables predicting that images belong to classes for which no labeled training instances are available. In this paper, we present a new ZSL framework that leverages both label attribute side information and a semantic label hierarchy. We present two methods, lifted zero-shot prediction and a custom conditional random field (CRF) model, that integrate both forms of side information. We propose benchmark tasks for this framework that focus on making predictions across a range of semantic levels. We show that lifted zero-shot prediction can dramatically outperform baseline methods when making predictions within specified semantic levels, and that the probability distribution provided by the CRF model can be leveraged to yield further performance improvements when making unconstrained predictions over the hierarchy.