IEEE

Hyperspectral Image Classification Based on a Locally Enhanced Transformer Network

Abstract: Recently, transformer-based models have achieved remarkable performance in hyperspectral image (HSI) classification. However, due to the limited training data, existing methods often show ...
news.gov.hk

Cultivating AI innovation on campus

Spearheaded by the Digital Policy Office, the IT Innovation Lab in Secondary Schools programme and the Knowing More About IT ...
Frontiers

Interpretable vision mamba for SAR images classification

Deep learning techniques have been successfully applied to object classification in Synthetic Aperture Radar (SAR) images, achieving remarkable performance. However, the current Transformer ...
VentureBeat

Microsoft launches MAI-Image-2-Efficient, a cheaper and faster AI image model

Microsoft is positioning MAI-Image-2-Efficient and its flagship MAI-Image-2 as complementary tools rather than replacements for each other — a tiered pairing designed to cover the full spectrum of ...
IEEE

Low-shot Image Classification Using Mixture of Experts

Abstract: We propose a low-shot image classification method called Limo, which can train an accurate image classification model under conditions of acute data scarcity. Limo uniquely assembles ...