Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discovery
This addresses a more realistic scenario in visual recognition by eliminating the need for pre-defined semantic labels for novel classes, though it is incremental in extending existing zero-shot learning frameworks.
The paper tackles the problem of novel visual category discovery without prior knowledge, proposing a Zero-Knowledge Zero-Shot Learning setting that classifies seen and unseen samples and recovers semantic attributes for novel categories, achieving superior performance on four benchmark datasets.
Generalized Zero-Shot Learning (GZSL) and Open-Set Recognition (OSR) are two mainstream settings that greatly extend conventional visual object recognition. However, the limitations of their problem settings are not negligible. The novel categories in GZSL require pre-defined semantic labels, making the problem setting less realistic; the oversimplified unknown class in OSR fails to explore the innate fine-grained and mixed structures of novel categories. In light of this, we are motivated to consider a new problem setting named Zero-Knowledge Zero-Shot Learning (ZK-ZSL) that assumes no prior knowledge of novel classes and aims to classify seen and unseen samples and recover semantic attributes of the fine-grained novel categories for further interpretation. To achieve this, we propose a novel framework that recovers the clustering structures of both seen and unseen categories where the seen class structures are guided by source labels. In addition, a structural alignment loss is designed to aid the semantic learning of unseen categories with their recovered structures. Experimental results demonstrate our method's superior performance in classification and semantic recovery on four benchmark datasets.