Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
Mohamed Elhoseiny,Babak Saleh,Ahmed Elgammal +2 more
- pp 2584-2591
Reads0
Chats0
TLDR
An approach for zero-shot learning of object categories where the description of unseen categories comes in the form of typical text such as an encyclopedia entry, without the need to explicitly defined attributes is proposed.Abstract:
The main question we address in this paper is how to use purely textual description of categories with no training images to learn visual classifiers for these categories. We propose an approach for zero-shot learning of object categories where the description of unseen categories comes in the form of typical text such as an encyclopedia entry, without the need to explicitly defined attributes. We propose and investigate two baseline formulations, based on regression and domain adaptation. Then, we propose a new constrained optimization formulation that combines a regression function and a knowledge transfer function with additional constraints to predict the classifier parameters for new classes. We applied the proposed approach on two fine-grained categorization datasets, and the results indicate successful classifier prediction.read more
Citations
More filters
Proceedings Article
Prototypical Networks for Few-shot Learning
TL;DR: Prototypical Networks as discussed by the authors learn a metric space in which classification can be performed by computing distances to prototype representations of each class, and achieve state-of-the-art results on the CU-Birds dataset.
Posted Content
Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly
TL;DR: A new zero-shot learning dataset is proposed, the Animals with Attributes 2 (AWA2) dataset which is made publicly available both in terms of image features and the images themselves and compares and analyzes a significant number of the state-of-the-art methods in depth.
Proceedings ArticleDOI
Learning Deep Representations of Fine-Grained Visual Descriptions
TL;DR: This model achieves strong performance on zero-shot text-based image retrieval and significantly outperforms the attribute-based state-of-the-art for zero- shot classification on the Caltech-UCSD Birds 200-2011 dataset.
Proceedings ArticleDOI
Low-Shot Visual Recognition by Shrinking and Hallucinating Features
Bharath Hariharan,Ross Girshick +1 more
TL;DR: This work presents a low-shot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild, and proposes representation regularization techniques and techniques to hallucinate additional training examples for data-starved classes.
Proceedings ArticleDOI
Semantic Autoencoder for Zero-Shot Learning
TL;DR: In this paper, an encoder aims to project a visual feature vector into the semantic space as in the existing ZSL models, but the decoder exerts an additional constraint, that the projection/code must be able to reconstruct the original visual feature.
References
More filters
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
WordNet: a lexical database for English
TL;DR: WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
Book
Gaussian Processes for Machine Learning
TL;DR: The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics, and deals with the supervised learning problem for both regression and classification.
Journal ArticleDOI
Term Weighting Approaches in Automatic Text Retrieval
Gerard Salton,Chris Buckley +1 more
TL;DR: This paper summarizes the insights gained in automatic term weighting, and provides baseline single term indexing models with which other more elaborate content analysis procedures can be compared.
Journal ArticleDOI
Ridge regression: biased estimation for nonorthogonal problems
TL;DR: In this paper, an estimation procedure based on adding small positive quantities to the diagonal of X′X was proposed, which is a method for showing in two dimensions the effects of nonorthogonality.