Leveraging the Invariant Side of Generative Zero-Shot Learning

by   Jingjing Li, et al.

Conventional zero-shot learning (ZSL) methods generally learn an embedding, e.g., visual-semantic mapping, to handle the unseen visual samples via an indirect manner. In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions. Specifically, we train a conditional Wasserstein GANs in which the generator synthesizes fake unseen features from noises and the discriminator distinguishes the fake from real via a minimax game. Considering that one semantic description can correspond to various synthesized visual samples, and the semantic description, figuratively, is the soul of the generated features, we introduce soul samples as the invariant side of generative zero-shot learning in this paper. A soul sample is the meta-representation of one class. It visualizes the most semantically-meaningful aspects of each sample in the same category. We regularize that each generated sample (the varying side of generative ZSL) should be close to at least one soul sample (the invariant side) which has the same class label with it. At the zero-shot recognition stage, we propose to use two classifiers, which are deployed in a cascade way, to achieve a coarse-to-fine result. Experiments on five popular benchmarks verify that our proposed approach can outperform state-of-the-art methods with significant improvements.


Imagine it for me: Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts

Most existing zero-shot learning methods consider the problem as a visua...

Bi-Semantic Reconstructing Generative Network for Zero-shot Learning

Many recent methods of zero-shot learning (ZSL) attempt to utilize gener...

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

Zero-shot learning strives to classify unseen categories for which no da...

Generative Adversarial Zero-shot Learning via Knowledge Graphs

Zero-shot learning (ZSL) is to handle the prediction of those unseen cla...

Alleviating Feature Confusion for Generative Zero-shot Learning

Lately, generative adversarial networks (GANs) have been successfully ap...

Structure-Aware Feature Generation for Zero-Shot Learning

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by lev...

Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches

Zero-shot learning (ZSL) is commonly used to address the very pervasive ...

Please sign up or login with your details

Forgot password? Click here to reset