Adaptive Relation-Aware Network for zero-shot classification

doi:10.1016/j.neunet.2024.106227

Adaptive Relation-Aware Network for zero-shot classification

2024-06-01

6

PRE

AI

DOI：10.1016/j.neunet.2024.106227

Original

Original request for help

Save

Abstract

En 中文

Supervised learning-based image classification in computer vision relies on visual samples containing a large amount of labeled information. Considering that it is labor-intensive to collect and label images and construct datasets manually, Zero-Shot Learning (ZSL) achieves knowledge transfer from seen categories to unseen categories by mining auxiliary information, which reduces the dependence on labeled image samples and is one of the current research hotspots in computer vision. However, most ZSL methods fail to properly measure the relationships between classes, or do not consider the differences and similarities between classes at all. In this paper, we propose Adaptive Relation-Aware Network (ARAN), a novel ZSL approach that incorporates the improved triplet loss from deep metric learning into a VAE-based generative model, which helps to model inter-class and intra-class relationships for different classes in ZSL datasets and generate an arbitrary amount of high-quality visual features containing more discriminative information. Moreover, we validate the effectiveness and superior performance of our ARAN through experimental evaluations under ZSL and more practical GZSL settings on three popular datasets AWA2, CUB, and SUN.

Keywords:

Zero-Shot Learning

Generative model

Adaptive

Relation-aware

Metric learning

Adaptive Relation-Aware Network for zero-shot classification

Abstract

Journal

Organization