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

Tiny object classification problem exists in many machine learningapplications like medical imaging or remote sensing, where the object ofinterest usually occupies a small region of the whole image. It is challengingto design an efficient machine learning model with respect to tiny object ofinterest. Current neural network structures are unable to deal with tiny objectefficiently because they are mainly developed for images featured by largescale objects. However, in quantum physics, there is a great theoreticalfoundation guiding us to analyze the target function for image classificationregarding to specific objects size ratio. In our work, we apply Tensor Networksto solve this arising tough machine learning problem. First, we summarize theprevious work that connects quantum spin model to image classification andbring the theory into the scenario of tiny object classification. Second, wepropose using 2D multi-scale entanglement renormalization ansatz (MERA) toclassify tiny objects in image. In the end, our experimental results indicatethat tensor network models are effective for tiny object classification problemand potentially will beat state-of-the-art. Our codes will be available onlinehttps://github.com/timqqt/MERA_Image_Classification.

Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification