GitHub

Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection

This project is released under Apache-2.0 License. If your method is based on Dinomaly, please acknowledge it in your work (papers, products, patents, competitions, etc.), preferably as a "Preliminary ...
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

HRS-Net: A Hybrid Multi-Scale Network Model Based on Convolution and Transformers for Multi-Class Retinal Disease Classification

Abstract: Optical coherence tomography (OCT) is an important basis for retinal diagnosis. Traditional OCT image analysis methods not only require a lot of manual ...
IEEE

Hybrid 3B Net and EfficientNetB2 Model for Multi-Class Brain Tumor Classification

Abstract: Brain tumor classification and diagnosis are critical for timely and effective treatment, as brain tumors can severely impact patient health and survival. This paper introduces an enhanced ...