Wildlife imaging shows that AI models aren't as smart as we think

Using AI to identify wildlife reveals a potential "transferability crisis," researchers say. Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across ...
IEEE

Spectral–Spatial Synergy Guided Attention Network for Hyperspectral Image Classification

Abstract: The attention mechanism has gained significant popularity in hyperspectral image classification (HSIC) for its ability to adaptively highlight key features. However, it often incurs ...
GitHub

Z80-μLM: A Retrocomputing Micro Language Model

Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of ram. The root behind this project ...
IEEE

BLTOO-MFFL: Automated and Adversarially Robust Deep Learning for SAR Image Classification by Bi-Level Three-Objective Optimization and Multi-Feature Fusion Loss

Abstract: The deep learning-based synthetic aperture radar (SAR) image classification model is vulnerable to adversarial attacks. Although automated deep learning (ADL) including neural architecture ...