Recurrent connectivity in the visual cortex is believed to aid object recognition for challenging conditions such as occlusion. Here we investigate if and how artificial neural networks also benefit from recurrence. We compare architectures composed of bottom-up, lateral and top-down connections and evaluate their performance using two novel stereoscopic occluded object datasets. We find that classification accuracy is significantly higher for recurrent models when compared to feedforward models of matched parametric complexity. Additionally we show that for challenging stimuli, the recurrent feedback is able to correctly revise the initial feedforward guess.
@article{arxiv.2104.10615,
title = {Recurrent Feedback Improves Recognition of Partially Occluded Objects},
author = {Markus Roland Ernst and Jochen Triesch and Thomas Burwick},
journal= {arXiv preprint arXiv:2104.10615},
year = {2021}
}
Comments
6 pages, 2 figures, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020). arXiv admin note: substantial text overlap with arXiv:1909.06175