Large Scale Metric Learning for Distance-Based Image Classification

This paper studies large-scale image classification, in a setting where new classes and training images could continuously be added at (near) zero cost. We cast this problem into one of learning a low-rank metric, which is shared across all classes and explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. We also introduce an extension of the NCM classifier to allow for richer image representations. Experiments on the ImageNet 2010 challenge dataset ---which contains more than 1M training images of 1K classes--- shows, surprisingly, that the NCM classifier compares favorably to the more flexible k-NN classifier. Moreover, the NCM performance suggests that 256 dimensional features is comparable to that of linear SVMs, which were used to obtain the current state-of-the-art performance. Experimentally we study the generalization performance to classes that were not used to learn the metrics, and show how a zero-shot model based on the ImageNet hierarchy can be combined effectively with small training datasets. Using a metric learned on 1K classes, we show results for the ImageNet-10K dataset, and obtain performance that is competitive with the current state-of-the-art, while requiring significant less training time.

Data and Resources

Additional Info

Field Value
Source https://inria.hal.science/hal-00735908
Author Mensink, Thomas, Verbeek, Jakob, Perronnin, Florent, Csurka, Gabriela
Maintainer CCSD
Last Updated November 1, 2026, 17:10 (UTC)
Created November 1, 2026, 17:10 (UTC)
Identifier Report N°: RR-8077
Language en
Rights https://about.hal.science/hal-authorisation-v1/
contributor Learning and recognition in vision (LEAR) ; Centre Inria de l'Université Grenoble Alpes ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK) ; Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP)-Centre National de la Recherche Scientifique (CNRS)
creator Mensink, Thomas
date 2012-09-27T00:00:00
harvest_object_id 874da309-a1c6-441c-baf1-27ed81c83fb9
harvest_source_id 3374d638-d20b-4672-ba96-a23232d55657
harvest_source_title test moissonnage SELUNE
metadata_modified 2026-10-23T00:00:00
set_spec type:REPORT