Semantic Feature Extraction for Generalized Zero-shot Learning
This addresses the challenge of identifying unseen classes in machine learning, but appears incremental as it builds on existing GZSL methods with specific enhancements.
The paper tackles the problem of generalized zero-shot learning (GZSL) by proposing a new technique called SE-GZSL that extracts semantic features to improve classification performance, showing it outperforms conventional approaches by a large margin in experiments.
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.