Semantic Feature Extraction for Generalized Zero-Shot Learning
Junhan Kim, Kyuhong Shim, Byonghyo Shim
[AAAI-22] Main Track
Abstract:
Generalized zero-shot learning (GZSL) is a learning technique to identify unseen classes by exploiting attributes. In this paper, we propose a new GZSL technique exploiting attribute-related image features. While conventional GZSL approaches use image features containing attribute-irrelevant information for the classification, our approach, henceforth referred to as semantic feature extraction-based GZSL (SE-GZSL), exploits semantic features, features containing only attribute-related information, to remove the interference caused by attribute-irrelevant information. To extract semantic features, we introduce 1) mutual information (MI)-based loss to capture all the attribute-related information in the image features and 2) similarity-based loss to remove attribute-irrelevant information. From extensive experiments on various benchmark datasets, we show that SE-GZSL outperforms conventional GZSL techniques.
Introduction Video
Sessions where this paper appears
-
Poster Session 1
Blue 4
-
Poster Session 11
Blue 4
