Attribute Prototype Network for Zero-Shot Learning

08/19/2020
by   Wenjia Xu, et al.
2

From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image representation with integrated attribute localization ability would be beneficial for zero-shot learning. To this end, we propose a novel zero-shot representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. We show that our locality augmented image representations achieve a new state-of-the-art on three zero-shot learning benchmarks. As an additional benefit, our model points to the visual evidence of the attributes in an image, e.g. for the CUB dataset, confirming the improved attribute localization ability of our image representation. The code will be publicaly available at https://wenjiaxu.github.io/APN-ZSL/.

READ FULL TEXT
research
04/04/2022

Attribute Prototype Network for Any-Shot Learning

Any-shot image classification allows to recognize novel classes with onl...
research
04/12/2018

A Large-scale Attribute Dataset for Zero-shot Learning

Zero-Shot Learning (ZSL) has attracted huge research attention over the ...
research
05/29/2023

Learning Conditional Attributes for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to train models to recogniz...
research
06/07/2018

Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning

In zero-shot learning (ZSL), a classifier is trained to recognize visual...
research
03/01/2019

Learning where to look: Semantic-Guided Multi-Attention Localization for Zero-Shot Learning

Zero-shot learning extends the conventional object classification to the...
research
05/04/2017

Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning

We propose a novel approach for unsupervised zero-shot learning (ZSL) of...
research
11/03/2021

Dual Progressive Prototype Network for Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) aims to recognize new categories w...

Please sign up or login with your details

Forgot password? Click here to reset