Multi-Label Zero-Shot Learning with Structured Knowledge Graphs

TL;DR

This paper introduces a deep learning model for multi-label zero-shot learning that leverages structured knowledge graphs to understand label relationships, enabling the prediction of unseen labels with improved accuracy.

Contribution

It presents a novel architecture that incorporates knowledge graphs for modeling label interdependencies in multi-label zero-shot learning tasks.

Findings

Achieves comparable or better performance than state-of-the-art methods.

Effectively models interdependencies between seen and unseen labels.

Demonstrates applicability to multi-label classification and zero-shot learning.

Abstract

In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge between objects of interests, we propose a framework that incorporates knowledge graphs for describing the relationships between multiple labels. Our model learns an information propagation mechanism from the semantic label space, which can be applied to model the interdependencies between seen and unseen class labels. With such investigation of structured knowledge graphs for visual reasoning, we show that our model can be applied for solving multi-label classification and ML-ZSL tasks. Compared to state-of-the-art approaches, comparable or improved performances can be achieved by our method.