Label-Embedding for Image Classification

03/30/2015
by   Zeynep Akata, et al.
0

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function that measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. Label embedding enjoys a built-in ability to leverage alternative sources of information instead of or in addition to attributes, such as e.g. class hierarchies or textual descriptions. Moreover, label embedding encompasses the whole range of learning settings from zero-shot learning to regular learning with a large number of labeled examples.

READ FULL TEXT

page 11

page 14

research
01/15/2022

Towards Zero-shot Sign Language Recognition

This paper tackles the problem of zero-shot sign language recognition (Z...
research
02/14/2019

Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification

Zero-shot learning (ZSL) is one of the most extreme forms of learning fr...
research
11/19/2018

Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning

In this paper, an adversarial erasing embedding network with the guidanc...
research
03/19/2015

Learning Hypergraph-regularized Attribute Predictors

We present a novel attribute learning framework named Hypergraph-based A...
research
05/03/2018

Multi-Context Label Embedding

Label embedding plays an important role in zero-shot learning. Side info...
research
10/05/2021

Multi-Objective Few-shot Learning for Fair Classification

In this paper, we propose a general framework for mitigating the dispari...
research
06/15/2021

Zero-sample surface defect detection and classification based on semantic feedback neural network

Defect detection and classification technology has changed from traditio...

Please sign up or login with your details

Forgot password? Click here to reset