Unsupervised spiking instance segmentation on event data using STDP features

Tools

Kirkland, Paul and Manna, Davide and Vicente Sola, Alex and Di Caterina, Gaetano (2022) Unsupervised spiking instance segmentation on event data using STDP features. IEEE Transactions on Computers, 71 (11). pp. 2728-2739. ISSN 0018-9340 (https://doi.org/10.1109/TC.2022.3191968)

[thumbnail of Kirkland-etal-IEEE-ToC-2022-Unsupervised-spiking-instance-segmentation-on-event]
Preview
 Text. Filename: Kirkland_etal_IEEE_ToC_2022_Unsupervised_spiking_instance_segmentation_on_event.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (15MB)| Preview

Abstract

Spiking Neural Networks (SNN) and the field of Neuromorphic Engineering has brought about a paradigm shift in how to approach Machine Learning (ML) and Computer Vision (CV) problem. This paradigm shift comes from the adaption of event-based sensing and processing. An event-based vision sensor allows for sparse and asynchronous events to be produced that are dynamically related to the scene. Allowing not only the spatial information but a high-fidelity of temporal information to be captured. Meanwhile avoiding the extra overhead and redundancy of conventional high frame rate approaches. However, with this change in paradigm, many techniques from traditional CV and ML are not applicable to these event-based spatial-temporal visual streams. As such a limited number of recognition, detection and segmentation approaches exist. In this paper, we present a novel approach that can perform instance segmentation using just the weights of a Spike Time Dependent Plasticity trained Spiking Convolutional Neural Network that was trained for object recognition. This exploits the spatial and temporal aspects of the SpikeSEG network's internal feature representations adding this new discriminative capability. We highlight the new capability by successfully transforming a single class unsupervised network for face detection into a multi-person face recognition and instance segmentation network.

ORCID iDs

Kirkland, Paul ORCID logoORCID: https://orcid.org/0000-0001-5905-6816, Manna, Davide ORCID logoORCID: https://orcid.org/0000-0001-8963-5050, Vicente Sola, Alex ORCID logoORCID: https://orcid.org/0000-0002-2370-6562 and Di Caterina, Gaetano ORCID logoORCID: https://orcid.org/0000-0002-7256-0897;
  • Item type:Article
    ID code:81825
    Dates:
    Date
    Event
    1 November 2022
    Published
    19 July 2022
    Published Online
    12 June 2022
    Accepted
    Notes:© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Engineering > Electronic and Electrical Engineering
    Depositing user: Pure Administrator
    Date deposited:11 Aug 2022 10:36
    Last modified:02 Dec 2024 01:27
    URI:https://strathprints.strath.ac.uk/id/eprint/81825
CORE (COnnecting REpositories)