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

Computer vision in general presented several advances such as trainingoptimizations, new architectures (pure attention, efficient block, visionlanguage models, generative models, among others). This have improvedperformance in several tasks such as classification, and others. However, themajority of these models focus on modifications that are taking distance fromrealistic neuroscientific approaches related to the brain. In this work, weadopt a more bio-inspired approach and present the Yin Yang ConvolutionalNetwork, an architecture that extracts visual manifold, its blocks are intendedto separate analysis of colors and forms at its initial layers, simulatingoccipital lobe's operations. Our results shows that our architecture providesState-of-the-Art efficiency among low parameter architectures in the datasetCIFAR-10. Our first model reached 93.32\% test accuracy, 0.8\% more than theolder SOTA in this category, while having 150k less parameters (726k in total).Our second model uses 52k parameters, losing only 3.86\% test accuracy. We alsoperformed an analysis on ImageNet, where we reached 66.49\% validation accuracywith 1.6M parameters. We make the code publicly available at:https://github.com/NoSavedDATA/YinYang_CNN.

Yin Yang Convolutional Nets: Image Manifold Extraction by the Analysis of Opposites