Tech Xplore

One tiny diode could shrink image sensors by adding memory and processing

P-n diodes are two-terminal devices that consist of two types of semiconductor materials (i.e., a p-type and an n-type ...
IEEE

HyCoT: A Transformer-Based Autoencoder for Hyperspectral Image Compression

Abstract: The development of learning-based hyperspectral image (HSI) compression models has recently attracted significant interest. Existing models predominantly utilize convolutional filters, which ...
Tech Xplore

Compression technique makes AI models leaner and faster while they're still learning

Training a large artificial intelligence model is expensive, not just in dollars, but in time, energy, and computational ...
IEEE

Fine-Tuning Vision Transformer Using LoRA for Image Classification

Abstract: This research paper focuses on fine-tuning a Vision Transformer (ViT) model using Low-Rank Adaptation (LoRA) for image classification tasks. LoRA offers an efficient alternative to ...