CoChat
Sign Up
Cited by 797Advanced Image and Video Retrieval TechniquesImage Retrieval and Classification TechniquesAdvanced Neural Network Applications

On feature combination for multiclass object classification

Gehler, Peter, Nowozin, Sebastian·2009·2009 IEEE 12th International Conference on Computer Vision
DOI 10.1109/iccv.2009.5459169
Open this paper in CoChat — free account

Abstract

A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem due to the high variability of visual appearance within each class. In the last years substantial performance gains on challenging benchmark datasets have been reported in the literature. This progress can be attributed to two developments: the design of highly discriminative and robust image features and the combination of multiple complementary features based on different aspects such as shape, color or texture. In this paper we study several models that aim at learning the correct weighting of different features from training data. These include multiple kernel learning as well as simple baseline methods. Furthermore we derive ensemble methods inspired by Boosting which are easily extendable to several multiclass setting. All methods are thoroughly evaluated on object classification datasets using a multitude of feature descriptors. The key results are that even very simple baseline methods, that are orders of magnitude faster than learning techniques are highly competitive with multiple kernel learning. Furthermore the Boosting type methods are found to produce consistently better results in all experiments. We provide insight of when combination methods can be expected to work and how the benefit of complementary features can be exploited most efficiently.

Integrity signals

Registry

Crossref · 10.1109/iccv.2009.5459169

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

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

Claims the paper makes

We couldn’t retrieve this paper’s full text, 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?

  • Simple additive or multiplicative averaging of kernels may reach the same level of performance as multiple kernel learning while being orders of magnitude faster.

    “At the same time, as shown by [39], simple additive or multiplicative averaging of kernels may reach the same level of performance while being orders of magnitude faster.”

    From ModDrop: Adaptive Multi-Modal Gesture Recognition (2016) · cites this paper as [39]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Gehler, P., & Nowozin, S.
Affiliations
Max Planck Institute for Biological Cybernetics (DE)
ORCID
Venue
2009 IEEE 12th International Conference on Computer Vision
Publisher
IEEE
Published
2009-09
Pages
221-228
DOI
10.1109/iccv.2009.5459169
OpenAlex
W2124372976
Cited by
797
References
5
Citations by year
2026: 1 · 2025: 8 · 2024: 7 · 2023: 7 · 2022: 11 · 2021: 24 · 2020: 17 · 2019: 31 · 2018: 41 · 2017: 58 · 2016: 79 · 2015: 76 · 2014: 114 · 2013: 112 · 2012: 77
FWCI
57.17
Type
conference paper
Language
en
Open access
closed
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • Max Planck Institute for Plasma Physics (submittedVersion)
  • MPG.PuRe (Max Planck Society) (submittedVersion)
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
feature combination, multiple kernel learning, boosting, ensemble methods, feature weighting, complementary features, visual object recognition, intra-class variation

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