Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions

One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of having to explicitly define these attributes. We present a new...

Full description

Saved in:
Bibliographic Details
Main Authors: Ba, Jimmy Lei, Swersky, Kevin, Fidler, Sanja, Salakhutdinov, Ruslan
Format: Conference Proceeding
Language:English
Subjects:
Categories
Computer vision
Descriptions
Electronic publishing
Encyclopedias
Internet
Learning
Mathematical models
Neural networks
Texts
Training
Visual
Visualization
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of having to explicitly define these attributes. We present a new model that can classify unseen categories from their textual description. Specifically, we use text features to predict the output weights of both the convolutional and the fully connected layers in a deep convolutional neural network (CNN). We take advantage of the architecture of CNNs and learn features at different layers, rather than just learning an embedding space for both modalities, as is common with existing approaches. The proposed model also allows us to automatically generate a list of pseudo-attributes for each visual category consisting of words from Wikipedia articles. We train our models end-to-end using the Caltech-UCSD bird and flower datasets and evaluate both ROC and Precision-Recall curves. Our empirical results show that the proposed model significantly outperforms previous methods.
ISSN:2380-7504
DOI:10.1109/ICCV.2015.483