Zero-shot Learning with Class Description Regularization

06/30/2021
by   Shayan Kousha, et al.
0

The purpose of generative Zero-shot learning (ZSL) is to learning from seen classes, transfer the learned knowledge, and create samples of unseen classes from the description of these unseen categories. To achieve better ZSL accuracies, models need to better understand the descriptions of unseen classes. We introduce a novel form of regularization that encourages generative ZSL models to pay more attention to the description of each category. Our empirical results demonstrate improvements over the performance of multiple state-of-the-art models on the task of generalized zero-shot recognition and classification when trained on textual description-based datasets like CUB and NABirds and attribute-based datasets like AWA2, aPY and SUN.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/01/2019

Creativity Inspired Zero-Shot Learning

Zero-shot learning (ZSL) aims at understanding unseen categories with no...
research
11/18/2020

A Multi-class Approach – Building a Visual Classifier based on Textual Descriptions using Zero-Shot Learning

Machine Learning (ML) techniques for image classification routinely requ...
research
03/17/2021

Large-Scale Zero-Shot Image Classification from Rich and Diverse Textual Descriptions

We study the impact of using rich and diverse textual descriptions of cl...
research
12/31/2022

DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning

Inspired by strategies like Active Learning, it is intuitive that intell...
research
10/21/2022

Generalizing over Long Tail Concepts for Medical Term Normalization

Medical term normalization consists in mapping a piece of text to a larg...
research
10/21/2019

Zero-shot Learning via Simultaneous Generating and Learning

To overcome the absence of training data for unseen classes, conventiona...
research
11/17/2022

Targeted Attention for Generalized- and Zero-Shot Learning

The Zero-Shot Learning (ZSL) task attempts to learn concepts without any...

Please sign up or login with your details

Forgot password? Click here to reset