Code release for "UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity"

Awesome Label-Efficient 3D Object Detection: A curated list of label-efficient 3D object detection: Unsupervised, Weakly-Supervised, Sparsely-Supervised, Semi-Supervised.

Machine learning movie recommending system

Analysis scripts for log data sets used in anomaly detection.

Official implementation of SuperSimpleNet [ICPR 2024, JIMS 2025]

Unsupervised Multi-modal Emotion Recognition System based on Momentum Contrast and Dual-reconstruction

This Model Classifies patient's diabetes level/severity in depth using 200k Samples from patients past patterns.

本项目实现了一种基于 VAE-CycleGAN 的图像重建无监督缺陷检测算法。该算法结合了变分自编码器 (VAE) 和 CycleGAN 的优势，无需标注数据即可检测图像中的缺陷/异常。This project implements an unsupervised defect detection algorithm for image reconstruction based on VAE-CycleGAN. This algorithm combines the advantages of variational autoencoders (VAE) and CycleGAN to detect defects in images without any supervision.

Unsupervised, one-shot, instance-based active contour/snake using deep learning features in python.

Delta Descriptors: Visual Localization via Visual Place Recognition (VPR) where places are described using a change-based spatio-temporal representation. (RA-L & IROS 2020)

Repository for the bisilhouette score R package

Course Material for Artificial Intelligence and Machine Learning - Unit 2 @ Computer Science Dept, Sapienza

Official PyTorch implementation of SynDiff described in the paper (https://arxiv.org/abs/2207.08208).

Latent Dirichlet Allocation via collapsed Gibbs sampling.

[MedIA 2024] This is a code implemention of the joint learning framework proposed in the manuscipt "Joint learning framework of cross-modal synthesis and diagnosis for Alzheimer's disease by mining underlying shared modality information".

Official implementation of the ECCV 2024 paper: TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection

This repository contains an implementation of a Recommendation System designed to provide recommendations using two main approaches: Content-Based Filtering (CBF) and Collaborative Filtering (CF). The system can be applied in a variety of use cases.

Model to evaluate the distribution of Regular Expressions (REs) across a ranked sequence list.

Implement of paper "Unsupervised Outlier Detection using Random Subspace and Subsampling Ensembles of Dirichlet Process Mixtures"

This repository contains the dataset for the corals analysis study and the notebooks for EDA, first pass, and final pass.