Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning

by   Zhiwu Lu, et al.

Zero-shot learning (ZSL) is made possible by learning a projection function between a feature space and a semantic space (e.g., an attribute space). Key to ZSL is thus to learn a projection that is robust against the often large domain gap between the seen and unseen class domains. In this work, this is achieved by unseen class data synthesis and robust projection function learning. Specifically, a novel semantic data synthesis strategy is proposed, by which semantic class prototypes (e.g., attribute vectors) are used to simply perturb seen class data for generating unseen class ones. As in any data synthesis/hallucination approach, there are ambiguities and uncertainties on how well the synthesised data can capture the targeted unseen class data distribution. To cope with this, the second contribution of this work is a novel projection learning model termed competitive bidirectional projection learning (BPL) designed to best utilise the ambiguous synthesised data. Specifically, we assume that each synthesised data point can belong to any unseen class; and the most likely two class candidates are exploited to learn a robust projection function in a competitive fashion. As a third contribution, we show that the proposed ZSL model can be easily extended to few-shot learning (FSL) by again exploiting semantic (class prototype guided) feature synthesis and competitive BPL. Extensive experiments show that our model achieves the state-of-the-art results on both problems.


Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to...

Domain-Invariant Projection Learning for Zero-Shot Recognition

Zero-shot learning (ZSL) aims to recognize unseen object classes without...

Visual Data Synthesis via GAN for Zero-Shot Video Classification

Zero-Shot Learning (ZSL) in video classification is a promising research...

Learning Robust Visual-semantic Mapping for Zero-shot Learning

Zero-shot learning (ZSL) aims at recognizing unseen class examples (e.g....

Convolutional Prototype Learning for Zero-Shot Recognition

Zero-shot learning (ZSL) has received increasing attention in recent yea...

Hierarchical Prototype Learning for Zero-Shot Recognition

Zero-Shot Learning (ZSL) has received extensive attention and successes ...

An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning

Zero-shot Learning (ZSL) classification categorizes or predicts classes ...

Please sign up or login with your details

Forgot password? Click here to reset