Learning by Associating Ambiguously Labeled Images
Authors:
- Zinan ZengZZZinan Zeng
- Shijie XiaoSXShijie Xiao
- Kui JiaKJKui Jia
- Tsung-Han ChanTCTsung-Han Chan
- Shenghua GaoSGShenghua Gao
- Dong XuDXDong Xu
- Yi MaYMYi Ma
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 708-715
Abstract
We study in this paper the problem of learning classifiers from ambiguously labeled images. For instance, in the collection of new images, each image contains some samples of interest (\emph{e.g.,} human faces), and its associated caption has labels with the true ones included, while the sample-label association is unknown. The task is to learn classifiers from these ambiguously labeled images and generalize to new images. An essential consideration here is how to make use of the information embedded in the relations between samples and labels, both within each image and across the image set. To this end, we propose a novel framework to address this problem. Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image. If we can identify samples of the same class from each image and associate them across the image set, the matrix formed by the samples from the same class would be ideally low-rank. By leveraging such a low-rank assumption, we can simultaneously optimize a partial permutation matrix (PPM) for each image, which is formulated in order to exploit all information between samples and labels in a principled way. The obtained PPMs can be readily used to assign labels to samples in training images, and then a standard SVM classifier can be trained and used for unseen data. Experiments on benchmark datasets show the effectiveness of our proposed method.Keywords
This publication has 18 references indexed in Scilit:
- Robust Recovery of Subspace Structures by Low-Rank RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Extended SRC: Undersampled Face Recognition via Intraclass Variant DictionaryIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Finding Correspondence from Multiple Images via Sparse and Low-Rank Decomposition2012
- Multi-task low-rank affinity pursuit for image segmentation2011
- Multi-Instance Multi-Label Learning for Image Classification with Large Vocabularies2011
- Automatic face naming with caption-based supervision2008
- Learning Structured Appearance Models from Captioned Images of Cluttered Scenes2007
- Hello! My name is... Buffy'' -- Automatic Naming of Characters in TV Video2006
- Optimal Point Correspondence through the Use of Rank Constraints2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004