Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes
Authors:
Open Access
- 7 July 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 39 (7) , 1360-1373
Abstract
In this paper, we present a label transfer model from texts to images for image classification tasks. The problem of image classification is often much more challenging than text classification. On one hand, labeled text data is more widely available than the labeled images for classification tasks. On the other hand, text data tends to have natural semantic interpretability, and they are often more directly related to class labels. On the contrary, the image features are not directly related to concepts inherent in class labels. One of our goals in this paper is to develop a model for revealing the functional relationships between text and image features as to directly transfer intermodal and intramodal labels to annotate the images. This is implemented by learning a transfer function as a bridge to propagate the labels between two multimodal spaces. However, the intermodal label transfers could be undermined by blindly transferring the labels of noisy texts to annotate images. To mitigate this problem, we present an intramodal label transfer process, which complements the intermodal label transfer by transferring the image labels instead when relevant text is absent from the source corpus. In addition, we generalize the inter-modal label transfer to zero-shot learning scenario where there are only text examples available to label unseen classes of images without any positive image examples. We evaluate our algorithm on an image classification task and show the effectiveness with respect to the other compared algorithms.Keywords
All Related Versions
Funding Information
- US National Science Foundation (16406218)
This publication has 31 references indexed in Scilit:
- Evaluation of output embeddings for fine-grained image classification2015
- Multimodal Similarity-Preserving HashingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Label-Embedding for Attribute-Based Classification2013
- Exploring Context and Content Links in Social Media: A Latent Space MethodIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Towards cross-category knowledge propagation for learning visual concepts2011
- Towards semantic knowledge propagation from text corpus to web images2011
- Learning semantic distance from community-tagged media collection2009
- Automated Flower Classification over a Large Number of Classes2008
- Self-taught learning2007
- Constructing informative priors using transfer learning2006