Semantic Feature Extraction for Generalized Zero-shot Learning

12/29/2021
by   Junhan Kim, et al.
165

Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly. Key idea of the proposed approach, henceforth referred to as semantic feature extraction-based GZSL (SE-GZSL), is to use the semantic feature containing only attribute-related information in learning the relationship between the image and the attribute. In doing so, we can remove the interference, if any, caused by the attribute-irrelevant information contained in the image feature. To train a network extracting the semantic feature, we present two novel loss functions, 1) mutual information-based loss to capture all the attribute-related information in the image feature and 2) similarity-based loss to remove unwanted attribute-irrelevant information. From extensive experiments using various datasets, we show that the proposed SE-GZSL technique outperforms conventional GZSL approaches by a large margin.

READ FULL TEXT

page 1

page 6

research
02/02/2023

Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) is a technique to train a deep lea...
research
03/06/2019

Transfer feature generating networks with semantic classes structure for zero-shot learning

Suffering from the generating feature inconsistence of seen classes trai...
research
09/24/2020

Attribute Propagation Network for Graph Zero-shot Learning

The goal of zero-shot learning (ZSL) is to train a model to classify sam...
research
12/01/2021

Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning

Current approaches to Zero-Shot Learning (ZSL) struggle to learn general...
research
08/01/2023

Zero-Shot Learning by Harnessing Adversarial Samples

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizin...
research
03/07/2022

MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning

The key challenge of zero-shot learning (ZSL) is how to infer the latent...
research
12/08/2017

Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning

We address zero-shot (ZS) learning, building upon prior work in hierarch...

Please sign up or login with your details

Forgot password? Click here to reset