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

How Microsoft shipped a production-optimized image model in under a month. The speed of this release deserves attention.
IEEE

SARCLIP: The First Vision–Language Foundation Model for SAR Image

Abstract: Foundation models have achieved remarkable breakthroughs across various domains, with the widely use of masked image modeling (MIM) and self-supervised learning (SSL). However, these models ...
IEEE

PGSMamba: Prompt-Guided Shuffle State Space Model for Hyperspectral Image Classification

Abstract: Hyperspectral image classification demands models capable of efficiently capturing complex spectral–spatial relationships and long-range dependencies. Despite significant advances in CNNs ...
IEEE

A Multiple Backbone Feature Fusion Ensemble CNN for Brain Tumor Detection and Classification from MRI Images

Abstract: Accurate classification of brain tumors from magnetic resonance imaging (MRI) scans is essential for early diagnosis and reliable clinical decision-making. However, variations in tumor ...
IEEE

Uncertainty-Aware Local Bayesian Framework for Hyperspectral Image Classification With Noisy Labels

Abstract: Various deep learning-based methods have greatly improved hyperspectral image (HSI) classification performance, but these models are sensitive to noisy training labels. Human annotation on ...
IEEE

Region-Relation Enhanced GNN-CNN for Image Classification

Abstract: Convolutional Neural Networks (CNNs) excel in local feature extraction but struggle to model regional semantic correlations and global context. This paper proposes a GNNintegrated framework ...
IEEE

CNNGP: Multi-tree Genetic Programming Integrating Pre-trained CNN Features for Fine-Grained Image Classification

Abstract: Fine-grained image classification (FGIC) remains a challenging task due to subtle inter-class differences and significant intra-class variations, particularly under limited training data.
IEEE

Hi-CIoTNet: A CNN-Based Hierarchical Model for IoT and Critical IoT Traffic Classification

Abstract: The growing number of Internet of Things (IoT) deployments has brought significant network heterogeneity and elevated traffic levels which make it difficult to identify and rank IoT network ...