Discriminative Embedding via Image-to-Class Distances

Xiantong Zhen, Ling Shao, Feng Zheng

Research output: Contribution to conferencePaper


Image-to-Class (I2C) distance firstly proposed in the naive Bayes nearest
neighbour (NBNN) classifier has shown its effectiveness in image classification.
However, due to the large number of nearest-neighbour search, I2C-based methods are extremely time-consuming, especially with highdimensional local features. In this paper, with the aim to improve and speed up I2C-based methods, we propose a novel discriminative embedding method based on I2C for local feature dimensionality reduction. Our method 1) greatly reduces the computational burden and improves the performance of I2C-based methods after reduction; 2) can well preserve the discriminative ability of local features, thanks to the use of I2C distances; and 3) provides an efficient closed-form solution by formulating the objective function as an eigenvector decomposition problem. We apply the proposed method to action recognition showing that it can significantly improve I2C-based classifiers.
Original languageEnglish
Publication statusPublished - 2014
Event25th British Machine Vision Conference, BMVC 2014 - Nottingham, United Kingdom
Duration: 1 Sep 20145 Sep 2014


Conference25th British Machine Vision Conference, BMVC 2014
Country/TerritoryUnited Kingdom

Cite this