Skip to Main content Skip to Navigation
Conference papers

Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost

Thomas Mensink 1, 2 Jakob Verbeek 1 Florent Perronnin 2 Gabriela Csurka 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : We are interested in large-scale image classification and especially in the setting where images corresponding to new or existing classes are continuously added to the training set. Our goal is to devise classifiers which can incorporate such images and classes on-the-fly at (near) zero cost. We cast this problem into one of learning a metric which is shared across all classes and explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. We learn metrics on the ImageNet 2010 challenge data set, which contains more than 1.2M training images of 1K classes. Surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier, and has comparable performance to linear SVMs. We also study the generalization performance, among others by using the learned metric on the ImageNet-10K dataset, and we obtain competitive performance. Finally, we explore zero-shot classification, and show how the zero-shot model can be combined very effectively with small training datasets.
Document type :
Conference papers
Complete list of metadata

Cited literature [28 references]  Display  Hide  Download
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Wednesday, August 1, 2012 - 11:41:55 AM
Last modification on : Tuesday, October 19, 2021 - 11:13:04 PM
Long-term archiving on: : Friday, November 2, 2012 - 2:30:50 AM

Files produced by the author(s)




Thomas Mensink, Jakob Verbeek, Florent Perronnin, Gabriela Csurka. Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost. ECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. pp.488-501, ⟨10.1007/978-3-642-33709-3_35⟩. ⟨hal-00722313⟩



Record views


Files downloads