Semantic Feature Extraction for Generalized Zero-Shot Learning


  • Junhan Kim Seoul National University
  • Kyuhong Shim Seoul National University
  • Byonghyo Shim Seoul National University



Computer Vision (CV)


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.




How to Cite

Kim, J., Shim, K., & Shim, B. (2022). Semantic Feature Extraction for Generalized Zero-Shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 1166-1173.



AAAI Technical Track on Computer Vision I