Semantic Feature Extraction for Generalized Zero-shot Learning

TL;DR

This paper introduces SE-GZSL, a novel approach for generalized zero-shot learning that extracts attribute-focused semantic features to improve classification accuracy, demonstrating significant performance gains over existing methods.

Contribution

The paper presents a new GZSL method using semantic feature extraction with two novel loss functions to enhance attribute relevance and reduce irrelevant information.

Findings

Outperforms conventional GZSL methods by a large margin

Effective removal of attribute-irrelevant information in features

Demonstrated robustness across various datasets

Abstract

Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly. Key idea of the proposed approach, henceforth referred to as semantic feature extraction-based GZSL (SE-GZSL), is to use the semantic feature containing only attribute-related information in learning the relationship between the image and the attribute. In doing so, we can remove the interference, if any, caused by the attribute-irrelevant information contained in the image feature. To train a network extracting the semantic feature, we present two novel loss functions, 1) mutual information-based loss to capture all the attribute-related information in the image feature and 2) similarity-based loss to remove unwanted attribute-irrelevant information. From extensive experiments using various datasets, we show that the proposed SE-GZSL technique outperforms conventional GZSL approaches by a large margin.