Large-scale image classification with trace-norm regularization

Zaid Harchaoui 1 Matthijs Douze 1, 2 Mattis Paulin 1 Miro Dudik 3 Jérôme Malick 4
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 NY
Yahoo! Labs New York
4 BIPOP - Modelling, Simulation, Control and Optimization of Non-Smooth Dynamical Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : With the advent of larger image classification datasets such as ImageNet, designing scalable and efficient multi-class classification algorithms is now an important challenge. We introduce a new scalable learning algorithm for large-scale multi-class image classification, based on the multinomial logistic loss and the trace-norm regularization penalty. Reframing the challenging non-smooth optimization problem into a surrogate infinite-dimensional optimization problem with a regular l1 -regularization penalty, we propose a simple and provably efficient accelerated coordinate descent algorithm. Furthermore, we show how to perform efficient matrix computations in the compressed domain for quantized dense visual features, scaling up to 100,000s examples, 1,000s-dimensional features, and 100s of categories. Promising experimental results on the "Fungus", "Ungulate", and "Vehicles" subsets of ImageNet are presented, where we show that our approach performs significantly better than state-of-the-art approaches for Fisher vectors with 16 Gaussians.
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-00728388
Contributor : Thoth Team <>
Submitted on : Wednesday, September 5, 2012 - 5:56:09 PM
Last modification on : Friday, February 22, 2019 - 11:44:20 AM
Long-term archiving on : Friday, December 16, 2016 - 10:22:31 AM

File

hdpdm_2012_ultrarod.pdf
Files produced by the author(s)

Identifiers

Citation

Zaid Harchaoui, Matthijs Douze, Mattis Paulin, Miro Dudik, Jérôme Malick. Large-scale image classification with trace-norm regularization. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2012, Providence, United States. pp.3386-3393, ⟨10.1109/CVPR.2012.6248078⟩. ⟨hal-00728388⟩

Share

Metrics

Record views

1322

Files downloads

1054