In defense of Nearest-Neighbor based image classification

State-of-the-art image classification methods require an intensive learning/training stage (using SVM, Boosting, etc.) In contrast, non-parametric nearest-neighbor (NN) based image classifiers require no training time and have other favorable properties. However, the large performance gap between th...

Full description

Saved in:
Bibliographic Details
Published in:2008 IEEE Conference on Computer Vision and Pattern Recognition pp. 1 - 8
Main Authors: Boiman, O., Shechtman, E., Irani, M.
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2008
Subjects:
Boosting
Classification tree analysis
Degradation
Image classification
Image databases
Neural networks
Quantization
Rendering (computer graphics)
Support vector machine classification
Support vector machines
ISBN:9781424422425, 1424422426
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:State-of-the-art image classification methods require an intensive learning/training stage (using SVM, Boosting, etc.) In contrast, non-parametric nearest-neighbor (NN) based image classifiers require no training time and have other favorable properties. However, the large performance gap between these two families of approaches rendered NN-based image classifiers useless. We claim that the effectiveness of non-parametric NN-based image classification has been considerably undervalued. We argue that two practices commonly used in image classification methods, have led to the inferior performance of NN-based image classifiers: (i) Quantization of local image descriptors (used to generate "bags-of-words ", codebooks). (ii) Computation of 'image-to-image' distance, instead of 'image-to-class' distance. We propose a trivial NN-based classifier - NBNN, (Naive-Bayes nearest-neighbor), which employs NN- distances in the space of the local image descriptors (and not in the space of images). NBNN computes direct 'image- to-class' distances without descriptor quantization. We further show that under the Naive-Bayes assumption, the theoretically optimal image classifier can be accurately approximated by NBNN. Although NBNN is extremely simple, efficient, and requires no learning/training phase, its performance ranks among the top leading learning-based image classifiers. Empirical comparisons are shown on several challenging databases (Caltech-101 ,Caltech-256 and Graz-01).
ISBN:9781424422425
1424422426
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2008.4587598