TY - JOUR AU - Kim, Junhan AU - Shim, Kyuhong AU - Shim, Byonghyo PY - 2022/06/28 Y2 - 2024/03/28 TI - Semantic Feature Extraction for Generalized Zero-Shot Learning JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 1 SE - AAAI Technical Track on Computer Vision I DO - 10.1609/aaai.v36i1.20002 UR - https://ojs.aaai.org/index.php/AAAI/article/view/20002 SP - 1166-1173 AB - 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. ER -