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 these two families of approaches rendered NNbased image classifiers useless. We claim that the effectiveness of non-parametric NNbased 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 NNdistances in the space of the local image descriptors (and not in the spac...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Oren Boiman, Eli Shechtman, Michal Irani
• Keywords: Computer Vision, CVPR 2008, Image Classifiers, Learning-based Image Classifiers, Local Image Descriptors, Nn-based Image Classifiers, Nnbased Image Classifiers