Skip to Main content Skip to Navigation
New interface
Journal articles

Distance-Based Image Classification: Generalizing to new classes at near-zero cost

Thomas Mensink 1 Jakob Verbeek 2 Florent Perronnin 3 Gabriela Csurka 3 
2 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 study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers, and introduce a new metric learning approach for the latter. We also introduce an extension of the NCM classifier to allow for richer class representations. Experiments on the ImageNet 2010 challenge dataset, which contains over 106 training images of 1,000 classes, show that, surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier. Moreover, the NCM performance is comparable to that of linear SVMs which obtain current state-of-the-art performance. Experimentally we study the generalization performance to classes that were not used to learn the metrics. Using a metric learned on 1,000 classes, we show results for the ImageNet-10K dataset which contains 10,000 classes, and obtain performance that is competitive with the current state-of-the-art, while being orders of magnitude faster. Furthermore, we show how a zero-shot class prior based on the ImageNet hierarchy can improve performance when few training images are available.
Document type :
Journal articles
Complete list of metadata

Cited literature [48 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Wednesday, April 24, 2013 - 9:59:44 AM
Last modification on : Saturday, November 19, 2022 - 3:59:08 AM
Long-term archiving on: : Monday, April 3, 2017 - 9:07:10 AM


Files produced by the author(s)



Thomas Mensink, Jakob Verbeek, Florent Perronnin, Gabriela Csurka. Distance-Based Image Classification: Generalizing to new classes at near-zero cost. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35 (11), pp.2624-2637. ⟨10.1109/TPAMI.2013.83⟩. ⟨hal-00817211⟩



Record views


Files downloads