Synthesized Classifiers for Zero-Shot Learning

@article{Changpinyo2016SynthesizedCF,
  title={Synthesized Classifiers for Zero-Shot Learning},
  author={Soravit Changpinyo and Wei-Lun Chao and Boqing Gong and Fei Sha},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={5327-5336}
}
Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning. Our main idea is to align the semantic space that is derived from external information to the model space that concerns itself with recognizing visual… 

Figures and Tables from this paper

Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning

This paper proposes a novel zero-shot learning model that takes advantage of clustering structures in the semantic embedding space to impose the structural constraint that semantic representations must be predictive of the locations of their corresponding visual exemplars.

Discriminative Latent Visual Space For Zero-Shot Object Classification

A novel encoder-decoder network is proposed to explore the possibility of learning an intermediate latent space for the visual features, which is deemed to be simultaneously reconstructive and discriminative.

Zero-shot classification with unseen prototype learning

This paper proposes a novel Unseen Prototype Learning (UPL) model, which is a simple yet effective framework to learn visual prototypes for unseen categories from the corresponding class-level semantic information, and the learned features are treated as latent classifiers directly.

Structurally Constrained Correlation Transfer for Zero-shot Learning

A novel zero-shot learning model is proposed that forms a neighborhood-preserving structure in the semantic embedding space and utilize it to predict classifiers for unseen classes and generates effective semantic representations and out-performs state-of-the-art methods.

Semi-supervised Zero-Shot Learning by a Clustering-based Approach

A novel semi-supervised zero-shot learning method that works on an embedding space corresponding to abstract deep visual features, such that the mapped signatures of the seen classes are close to labeled samples of the corresponding classes and unlabeled data are also close to the mapped signature of one of the unseen classes.

Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition

This work proposes a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, where the discriminative information lying in the visual space is utilized to improve the less discrim inative semantic space.

Joint Concept Matching based Learning for Zero-Shot Recognition

It is shown that all these constraints on the latent space, class-specific knowledge, reconstruction of features and their combinations enhance the robustness against the projection domain shift problem, and improve the generalization ability to unseen object classes.
...

References

SHOWING 1-10 OF 63 REFERENCES

Zero-Shot Learning Through Cross-Modal Transfer

This work introduces a model that can recognize objects in images even if no training data is available for the object class, and uses novelty detection methods to differentiate unseen classes from seen classes.

Semi-Supervised Zero-Shot Classification with Label Representation Learning

A novel zero-shot classification approach that automatically learns label embeddings from the input data in a semi-supervised large-margin learning framework that tackles the target prediction problem directly without introducing intermediate prediction problems.

Zero-Shot Learning via Semantic Similarity Embedding

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label

Zero-Shot Learning via Joint Latent Similarity Embedding

A joint discriminative learning framework based on dictionary learning is developed to jointly learn the parameters of the model for both domains, which ultimately leads to a class-independent classifier that shows 4.90% improvement over the state-of-the-art in accuracy averaged across four benchmark datasets.

Transductive Multi-View Zero-Shot Learning

A novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space that rectifies the projection shift between the auxiliary and target domains, exploits the complementarity of multiple semantic representations, and significantly outperforms existing methods for both zero- shot and N-shot recognition.

Zero-shot object recognition by semantic manifold distance

The semantic manifold structure is used to redefine the distance metric in the semantic embedding space for more effective ZSL, and the proposed new model improves upon and seamlessly unifies various existing ZSL algorithms.

Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks

This work uses zero-shot classifiers to guide the learning process by linking the new task to the the existing classifiers, and proposes an effective active learning algorithm which learns the best possible target classification model with minimum human labeling effort.

Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation

This paper proposes a novel framework, transductive multi-view embedding, that rectifies the projection shift between the auxiliary and target domains, exploits the complementarity of multiple semantic representations, achieves state-of-the-art recognition results on image and video benchmark datasets, and enables novel cross-view annotation tasks.

Attribute-Based Classification for Zero-Shot Visual Object Categorization

We study the problem of object recognition for categories for which we have no training examples, a task also called zero--data or zero-shot learning. This situation has hardly been studied in

UvA-DARE ( Digital Academic Repository ) Active Transfer Learning with Zero-Shot Priors : Reusing Past Datasets for Future

This work uses zero-shot classifiers to guide the learning process by linking the new task to the existing classifiers, and proposes an effective active learning algorithm which learns the best possible target classification model with minimum human labeling effort.
...