Pipeline training and inference Anomalib models UI in Anomaly Detection

PatchCore method for Industrial Anomaly Detection + CLIP

Optimized PaDim based on Anodet

An unofficial implementation using Pytorch for "Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types". Improve the algorithm with DINO pretrained ViT. Implement algorithms based on PatchCore.

Comprehensive benchmark for anomaly detection models on MVTec AD dataset using Anomalib. Includes PatchCore, EfficientAD, FastFlow, STFPM, PaDiM with Gradio demo.

📸🔥Thermal Camera Diagnosis App Prototype was my bachelor thesis project at THU, focused on enhancing battery recycling processes using thermal imaging anomaly detection.

Unsupervised maize disease detection with cross-domain evaluation on real-field PlantDoc imagery and a controlled background-sensitivity experiment. PatchCore generalizes from lab to field (AUROC 0.9995); reconstruction-based methods are 4× inflated by domain shift.

Industrial anomaly detection system using PatchCore-based feature extraction and memory bank modeling for visual defect localization.

Premium-quality notebooks for practical anomaly detection with Autoencoders, PatchCore, and DRÆM. Built for engineers, data teams, and SMEs adopting AI-powered inspection.

An industry-style proof of concept for welding anomaly detection using unsupervised PatchCore, featuring explainable heatmaps for visual interpretation of defects.

Real-time manufacturing defect detection using unsupervised PatchCore — FastAPI + Streamlit + OpenVINO

Unsupervised visual anomaly detection using PatchCore on MVTec AD, achieves 99.1% AUROC on bottle defect detection without any anomaly labels during training

Edge anomaly detection for video streams with multi-backend inference benchmarking (TensorRT, ONNX, PyTorch)

A focused fork of an anomaly detection library, dedicated to enhancing and extending the PatchCore model.

Anomaly Detection with Localization developed for the Machine Learning for Vision and Multimedia course @polito. Tech stack: PyTorch, Python.

Industrial anomaly detection: PatchCore, FastFlow, EfficientAD on MVTec benchmark

A PyTorch-based framework for unsupervised anomaly detection on the MVTec AD dataset. Implements PaDiM, PatchCore, FastFlow, and AutoEncoder models with utilities for dataset preparation, training, evaluation, and reporting.

Unsupervised and semi-supervised anomaly detection on industrial surface defects using PatchCore and autoencoder baselines

OrbitCore: Perspective- and illumination-invariant PatchCore for dynamic environments.

Clean reproduction of PatchCore (Roth et al., CVPR 2022) on MVTec-AD with image-level AUROC, pixel-level AUROC, and pixel-level AUPRO. First in a series of visual anomaly detection reproductions.