Generalised Zero-Shot Learning with a Classifier Ensemble over Multi-Modal Embedding Spaces

by   Rafael Felix, et al.

Generalised zero-shot learning (GZSL) methods aim to classify previously seen and unseen visual classes by leveraging the semantic information of those classes. In the context of GZSL, semantic information is non-visual data such as a text description of both seen and unseen classes. Previous GZSL methods have utilised transformations between visual and semantic embedding spaces, as well as the learning of joint spaces that include both visual and semantic information. In either case, classification is then performed on a single learned space. We argue that each embedding space contains complementary information for the GZSL problem. By using just a visual, semantic or joint space some of this information will invariably be lost. In this paper, we demonstrate the advantages of our new GZSL method that combines the classification of visual, semantic and joint spaces. Most importantly, this ensembling allows for more information from the source domains to be seen during classification. An additional contribution of our work is the application of a calibration procedure for each classifier in the ensemble. This calibration mitigates the problem of model selection when combining the classifiers. Lastly, our proposed method achieves state-of-the-art results on the CUB, AWA1 and AWA2 benchmark data sets and provides competitive performance on the SUN data set.


Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space

Generalised zero-shot learning (GZSL) is a classification problem where ...

Not just a matter of semantics: the relationship between visual similarity and semantic similarity

Knowledge transfer, zero-shot learning and semantic image retrieval are ...

Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize novel classes by transferring...

Multi-modal Ensemble Classification for Generalized Zero Shot Learning

Generalized zero shot learning (GZSL) is defined by a training process c...

Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation

We address the problem of generalized zero-shot semantic segmentation (G...

Prototypical Model with Novel Information-theoretic Loss Function for Generalized Zero Shot Learning

Generalized zero shot learning (GZSL) is still a technical challenge of ...

What Remains of Visual Semantic Embeddings

Zero shot learning (ZSL) has seen a surge in interest over the decade fo...

Please sign up or login with your details

Forgot password? Click here to reset