Logo image
Integrated generalized zero-shot learning for fine-grained classification
Journal article   Peer reviewed

Integrated generalized zero-shot learning for fine-grained classification

T. Shermin, S.W. Teng, F. Sohel, M. Murshed and G. Lu
Pattern Recognition, Vol.122, Art. 108246
2022
url
Link to Published Version *Subscription may be requiredView

Abstract

Embedding learning (EL) and feature synthesizing (FS) are two of the popular categories of fine-grained GZSL methods. EL or FS using global features cannot discriminate fine details in the absence of local features. On the other hand, EL or FS methods exploiting local features either neglect direct attribute guidance or global information. Consequently, neither method performs well. In this paper, we propose to explore global and direct attribute-supervised local visual features for both EL and FS categories in an integrated manner for fine-grained GZSL. The proposed integrated network has an EL sub-network and a FS sub-network. Consequently, the proposed integrated network can be tested in two ways. We propose a novel two-step dense attention mechanism to discover attribute-guided local visual features. We introduce new mutual learning between the sub-networks to exploit mutually beneficial information for optimization. Moreover, we propose to compute source-target class similarity based on mutual information and transfer-learn the target classes to reduce bias towards the source domain during testing. We demonstrate that our proposed method outperforms contemporary methods on benchmark datasets.

Details

Metrics

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
Citation topics
4 Electrical Engineering, Electronics & Computer Science
4.17 Computer Vision & Graphics
4.17.2789 Generative Image Synthesis
Web Of Science research areas
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
ESI research areas
Engineering
Logo image