Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning

TL;DR

This paper introduces a semantic enhanced knowledge graph combined with a Residual Graph Convolutional Network to improve large-scale zero-shot learning, addressing over-smoothing and scalability issues, achieving state-of-the-art results.

Contribution

It proposes a novel semantic enhanced knowledge graph and a Residual GCN to better model category correlations and facilitate new category addition in zero-shot learning.

Findings

Achieved state-of-the-art performance on ImageNet-21K and AWA2 datasets.

Demonstrated improved generalization and robustness across various feature extraction networks.

Effectively alleviated over-smoothing in deep graph convolutional networks.

Abstract

Zero-Shot Learning has been a highlighted research topic in both vision and language areas. Recently, most existing methods adopt structured knowledge information to model explicit correlations among categories and use deep graph convolutional network to propagate information between different categories. However, it is difficult to add new categories to existing structured knowledge graph, and deep graph convolutional network suffers from over-smoothing problem. In this paper, we provide a new semantic enhanced knowledge graph that contains both expert knowledge and categories semantic correlation. Our semantic enhanced knowledge graph can further enhance the correlations among categories and make it easy to absorb new categories. To propagate information on the knowledge graph, we propose a novel Residual Graph Convolutional Network (ResGCN), which can effectively alleviate the problem of over-smoothing. Experiments conducted on the widely used large-scale ImageNet-21K dataset and AWA2 dataset show the effectiveness of our method, and establish a new state-of-the-art on zero-shot learning. Moreover, our results on the large-scale ImageNet-21K with various feature extraction networks show that our method has better generalization and robustness.