Attribute Alignment and Enhancement for Generalized Zero-Shot Learning

Nannan Lu, MingKai Qiu

Keywords: zero-shot learning, image classification, attribute alignment, graph neural network, attention network

Abstract: Generalized zero-shot learning (GZSL) aims to recognize both seen and unseen classes, which challenges the generalization ability of a model. In this paper, we propose a novel approach to fully utilize attributes information, referred to as attribute alignment and enhancement (A3E) network. It contains two modules. First, attribute localization (AL) module utilizes the supervision of class attribute vectors to guide visual localization for attributes through the implicit localization capability within the feature extractor, and the visual features corresponding to the attributes (attribute-visual features) are obtained. Second, enhanced attribute scoring (EAS) module employs the supervision of the attribute word vectors (attribute semantics) to project input attribute visual features to attribute semantic space using Graph Attention Network (GAT). Based on the constructed attribute relation graph (ARG), EAS module generates enhanced representation of attributes. Experiments on standard datasets demonstrate that the enhanced attribute representation greatly improves the classification performance, which helps A3E to achieve state-of-the-art performances in both ZSL and GZSL tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning