• Corpus ID: 202558574

Semantic Similarity Based Softmax Classifier for Zero-Shot Learning

  title={Semantic Similarity Based Softmax Classifier for Zero-Shot Learning},
  author={Shabnam Daghaghi and Tharun Medini and Anshumali Shrivastava},
Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information (or description) about seen and unseen classes, often in the form of physically realizable or descriptive attributes. Lack of any single training example from a set of classes prohibits use of standard classification techniques and losses, including the popular crossentropy loss. Currently, state-of-the-art approaches… 
A Review of Generalized Zero-Shot Learning Methods
This review paper presents a hierarchical categorization of the GZSL methods and discusses the representative methods of each category, and discusses several research directions for future studies.


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.
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
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.
Synthesized Classifiers for Zero-Shot Learning
This work introduces a set of "phantom" object classes whose coordinates live in both the semantic space and the model space and demonstrates superior accuracy of this approach over the state of the art on four benchmark datasets for zero-shot learning.
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.
Zero-Shot Classification with Discriminative Semantic Representation Learning
  • Meng Ye, Yuhong Guo
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
This paper proposes a novel zero-shot learning method based on discriminative sparse non-negative matrix factorization, and develops a label propagation based testing procedure to classify the unlabeled instances from the unseen classes in the target domain.
COSTA: Co-Occurrence Statistics for Zero-Shot Classification
The main contribution is COSTA, which exploits co-occurrences of visual concepts in images for knowledge transfer, which estimates a classifier for a new label, as a weighted combination of related classes, using the co-Occurrences to define the weight.
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
It is shown that there is a large gap between the performance of existing approaches and the performance limit of GZSL, suggesting that improving the quality of class semantic embeddings is vital to improving ZSL.
Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication
The proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a metric learning problem, and gives state-of-the-art results on four challenging datasets used for zero- shot recognition evaluation.
Generalized Zero-Shot Learning with Deep Calibration Network
This paper proposes a novel Deep Calibration Network (DCN) approach towards this generalized zero-shot learning paradigm, which enables simultaneous calibration of deep networks on the confidence of source classes and uncertainty of target classes.