Learning Clusterable Visual Features for Zero-Shot Recognition

10/07/2020
by   Jingyi Xu, et al.
5

In zero-shot learning (ZSL), conditional generators have been widely used to generate additional training features. These features can then be used to train the classifiers for testing data. However, some testing data are considered "hard" as they lie close to the decision boundaries and are prone to misclassification, leading to performance degradation for ZSL. In this paper, we propose to learn clusterable features for ZSL problems. Using a Conditional Variational Autoencoder (CVAE) as the feature generator, we project the original features to a new feature space supervised by an auxiliary classification loss. To further increase clusterability, we fine-tune the features using Gaussian similarity loss. The clusterable visual features are not only more suitable for CVAE reconstruction but are also more separable which improves classification accuracy. Moreover, we introduce Gaussian noise to enlarge the intra-class variance of the generated features, which helps to improve the classifier's robustness. Our experiments on SUN,CUB, and AWA2 datasets show consistent improvement over previous state-of-the-art ZSL results by a large margin. In addition to its effectiveness on zero-shot classification, experiments show that our method to increase feature clusterability benefits few-shot learning algorithms as well.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2020

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

Zero-shot object recognition or zero-shot learning aims to transfer the ...
research
02/26/2021

Zero-Shot Learning Based on Knowledge Sharing

Zero-Shot Learning (ZSL) is an emerging research that aims to solve the ...
research
09/13/2019

Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

Zero-shot learning (ZSL) aims to recognize instances of unseen classes s...
research
04/10/2020

SR2CNN: Zero-Shot Learning for Signal Recognition

Signal recognition is one of significant and challenging tasks in the si...
research
06/14/2018

Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems

This paper presents two ways of dealing with scarce data in semantic dec...
research
04/22/2019

Learning Feature-to-Feature Translator by Alternating Back-Propagation for Zero-Shot Learning

We investigate learning feature-to-feature translator networks by altern...
research
06/12/2018

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

It is one typical and general topic of learning a good embedding model t...

Please sign up or login with your details

Forgot password? Click here to reset