This paper presents the novel combination of a visual transformer style patch classifier with saccaded local attention. A novel optimisation paradigm for training object models is also presented, rather than the optimisation function minimising class membership probability error the network is trained to estimate the normalised distance to the centroid of labelled objects. This approach builds a degree of transnational invariance directly into the model and allows fast saccaded search with gradient ascent to find object centroids. The resulting saccaded visual transformer is demonstrated on human faces.
@article{arxiv.2210.09220,
title = {A Saccaded Visual Transformer for General Object Spotting},
author = {Willem. T. Pye and David. A. Sinclair},
journal= {arXiv preprint arXiv:2210.09220},
year = {2022}
}
Comments
11 pages mostly figure, central idea is to train on distance a patch is form a labelled feature