CoChat

High-dimensional signature compression for large-scale image classification

Sanchez, Jorge, Perronnin, Florent · 2011 · CVPR 2011

The DOI matches its Crossref record; 33 of the 34 references it cites were found in a registry or an index.

Abstract

We address image classification on a large-scale, i.e. when a large number of images and classes are involved. First, we study classification accuracy as a function of the image signature dimensionality and the training set size. We show experimentally that the larger the training set, the higher the impact of the dimensionality on the accuracy. In other words, high-dimensional signatures are important to obtain state-of-the-art results on large datasets. Second, we tackle the problem of data compression on very large signatures (on the order of 105dimensions) using two lossy compression strategies: a dimensionality reduction technique known as the hash kernel and an encoding technique based on product quantizers. We explain how the gain in storage can be traded against a loss in accuracy and/or an increase in CPU cost. We report results on two large databases - ImageNet and a dataset of lM Flickr images - showing that we can reduce the storage of our signatures by a factor 64 to 128 with little loss in accuracy. Integrating the decompression in the classifier learning yields an efficient and scalable training algorithm. On ILSVRC2010 we report a 74.3% accuracy at top-5, which corresponds to a 2.5% absolute improvement with respect to the state-of-the-art. On a subset of 10K classes of ImageNet we report a top-1 accuracy of 16.7%, a relative improvement of 160% with respect to the state-of-the-art.

Overview

Integrity signals

Registry

Crossref · 10.1109/cvpr.2011.5995504

Cites

33 of 33 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 33 references

Research works printed but not linked: 6

  1. shi, 2009, Hash kernels, AISTATS
  2. bottou, 0, SGD
  3. berg, 2010, ILSVRC
  4. gong, 2009, Image classification using Gaussian mixture and local coordinate coding, PASCAL VOC 2009 Workshop
  5. everingham, 0, The PASCAL VOC 2008 Results
  6. everingham, 2007, The PASCAL VOC

Cited by

Metadata

Authors
Sanchez, J., & Perronnin, F.
Affiliations
Xerox (France) (FR)
Venue
CVPR 2011
Publisher
IEEE
Published
2011-06
Pages
1665-1672
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2053229256
Cited by
272
References
34
Citations by year
2026: 3 · 2025: 5 · 2024: 7 · 2023: 6 · 2022: 11 · 2021: 19 · 2020: 10 · 2019: 23 · 2018: 17 · 2017: 23 · 2016: 21 · 2015: 46 · 2014: 30 · 2013: 30 · 2012: 18
FWCI
19.28
Type
conference paper
Language
en
Open access
closed
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
image classification, large-scale image classification, signature compression, lossy compression, dimensionality reduction, training data size, storage efficiency, scalable training, ImageNet, Flickr images

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.