English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Spiking neural networks (SNNs) have rich spatial-temporal dynamics, which aresuitable for processing neuromorphic, event-based data. However, event-baseddatasets are usually less annotated than static datasets used in traditionaldeep learning. Small data scale makes SNNs prone to overfitting and limits theperformance of the SNN. To enhance the generalizability of SNNs on event-baseddatasets, we propose a knowledge-transfer framework that leverages staticimages to assist in the training on neuromorphic datasets. Our method proposesdomain loss and semantic loss to exploit both domain-invariant and uniquefeatures of these two domains, providing SNNs with more generalized knowledgefor subsequent targeted training on neuromorphic data. Specifically, domainloss aligns the feature space and aims to capture common features betweenstatic and event-based images, while semantic loss emphasizes that thedifferences between samples from different categories should be as large aspossible. Experimental results demonstrate that our method outperforms existingmethods on all mainstream neuromorphic vision datasets. In particular, weachieve significant performance improvement of 2.7\% and 9.8\% when using only10\% training data of CIFAR10-DVS and N-Caltech 101 datasets, respectively.

Improving the Performance of Spiking Neural Networks on Event-based Datasets with Knowledge Transfer