An Encoding Framework for Binarized Images using HyperDimensional Computing

TL;DR

This article proposes a novel lightweight approach relying only on native HD arithmetic vector operations to encode binarized images that preserves the similarity of patterns at nearby locations by using point of interest selection and local linear mapping.

Abstract

Hyperdimensional Computing (HDC) is a brain-inspired and light-weight machine learning method. It has received significant attention in the literature as a candidate to be applied in the wearable internet of things, near-sensor artificial intelligence applications and on-device processing. HDC is computationally less complex than traditional deep learning algorithms and typically achieves moderate to good classification performance. A key aspect that determines the performance of HDC is the encoding of the input data to the hyperdimensional (HD) space. This article proposes a novel light-weight approach relying only on native HD arithmetic vector operations to encode binarized images that preserves similarity of patterns at nearby locations by using point of interest selection and local linear mapping. The method reaches an accuracy of 97.35% on the test set for the MNIST data set and 84.12% for the Fashion-MNIST data set. These results outperform other studies using baseline HDC with different encoding approaches and are on par with more complex hybrid HDC models. The proposed encoding approach also demonstrates a higher robustness to noise and blur compared to the baseline encoding.

Figures (2)

• Figure 1: Similarity of all pixel's position vector to position vector of pixel at location (21,11) for an image of size 28x28 that are encoded as $\textbf{v}_{x} \otimes \textbf{v}_{y}$ of which the x and y positions are mapped to vectors with (a) orthogonal mapping, (b) linear mappingKleyko2018bRahimi2016a, (c) the concatenation approach of Rachkovskij2005aNeubert2021a using 10 edge vectors for each axis (dotted lines) and (d) our proposed approach of local linear mapping with 9 splits and thus 10 edge vectors (dotted lines).
• Figure 2: Schematic overview of the proposed unified encoding framework for a training sample of the MNIST data set with size 28x28 using a patch size of 3x3 around the POIs ($z = 3$, $h = 28$ and $w = 28$).