DeepAI AI Chat
Log In Sign Up

Disentangling Semantic-to-visual Confusion for Zero-shot Learning

by   Zihan Ye, et al.

Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss (TL) is popularly used to generate realistic visual distributions from semantics by automatically searching discriminative representations. However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL. To alleviate this drawback, we propose in this work a multi-modal triplet loss (MMTL) which utilizes multimodal information to search a disentangled representation space. As such, all classes can interplay which can benefit learning disentangled class representations in the searched space. Furthermore, we develop a novel model called Disentangling Class Representation Generative Adversarial Network (DCR-GAN) focusing on exploiting the disentangled representations in training, feature synthesis, and final recognition stages. Benefiting from the disentangled representations, DCR-GAN could fit a more realistic distribution over both seen and unseen features. Extensive experiments show that our proposed model can lead to superior performance to the state-of-the-arts on four benchmark datasets. Our code is available at


page 2

page 13


Multi-modal Cycle-consistent Generalized Zero-Shot Learning

In generalized zero shot learning (GZSL), the set of classes are split i...

SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning

The existing Zero-Shot learning (ZSL) methods may suffer from the vague ...

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) is a challenging class of vision a...

Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification

New categories can be discovered by transforming semantic features into ...

Conditional MoCoGAN for Zero-Shot Video Generation

We propose a conditional generative adversarial network (GAN) model for ...

Generative Hierarchical Features from Synthesizing Images

Generative Adversarial Networks (GANs) have recently advanced image synt...

Learning Deep Disentangled Embeddings with the F-Statistic Loss

Deep-embedding methods aim to discover representations of a domain that ...