Structure propagation for zero-shot learning

by   Guangfeng Lin, et al.

The key of zero-shot learning (ZSL) is how to find the information transfer model for bridging the gap between images and semantic information (texts or attributes). Existing ZSL methods usually construct the compatibility function between images and class labels with the consideration of the relevance on the semantic classes (the manifold structure of semantic classes). However, the relationship of image classes (the manifold structure of image classes) is also very important for the compatibility model construction. It is difficult to capture the relationship among image classes due to unseen classes, so that the manifold structure of image classes often is ignored in ZSL. To complement each other between the manifold structure of image classes and that of semantic classes information, we propose structure propagation (SP) for improving the performance of ZSL for classification. SP can jointly consider the manifold structure of image classes and that of semantic classes for approximating to the intrinsic structure of object classes. Moreover, the SP can describe the constrain condition between the compatibility function and these manifold structures for balancing the influence of the structure propagation iteration. The SP solution provides not only unseen class labels but also the relationship of two manifold structures that encode the positive transfer in structure propagation. Experimental results demonstrate that SP can attain the promising results on the AwA, CUB, Dogs and SUN databases.


page 1

page 2

page 3

page 4


Transfer feature generating networks with semantic classes structure for zero-shot learning

Suffering from the generating feature inconsistence of seen classes trai...

Class label autoencoder for zero-shot learning

Existing zero-shot learning (ZSL) methods usually learn a projection fun...

Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths

Zero-shot recognition aims to accurately recognize objects of unseen cla...

For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions

It is well established that training deep neural networks gives useful r...

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

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

Zero Shot Hashing

This paper provides a framework to hash images containing instances of u...

Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes

In this paper, we present a label transfer model from texts to images fo...

Please sign up or login with your details

Forgot password? Click here to reset