Hardware Compliant Approximate Image Codes

Da Kuang, Alex Gittens, Raffay Hamid; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 924-932


In recent years, several feature encoding schemes for the bags-of-visual-words model have been proposed. While most of these schemes produce impressive results, they all share an important limitation: their high computational complexity makes it challenging to use them for large-scale problems. In this work, we propose an approximate locality-constrained encoding scheme that offers significantly better computational efficiency (~40x) than its exact counterpart, with comparable classification accuracy. Using the perturbation analysis of least-squares problems, we present a formal approximation error analysis of our approach, which helps distill the intuition behind the robustness of our method. We present a thorough set of empirical analyses on multiple standard data-sets, to assess the capability of our encoding scheme for its representational as well as discriminative accuracy.

Related Material

author = {Kuang, Da and Gittens, Alex and Hamid, Raffay},
title = {Hardware Compliant Approximate Image Codes},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}