This repository is an unofficial implementation of the network described in Wang, G., Han, S., Ding, E., & Huang, D. (2021). Student-Teacher Feature Pyramid Matching for Anomaly Detection. The British Machine Vision Conference (BMVC).

Godot C# frontend and FastApi pytorch backend for detecting anomaly region in MVTec dataset.

Reorganize KolektorSDD dataset as MVTecAD dataset's format. Report SOTA anomaly detection models in KolektorSDD.

Source code for my master thesis "Anomaly detection with Convolutional Autoencoder"

Keras implementation of AnoGAN model.

반도체 소자 이상 탐지 AI 경진대회, DACON (2024.02.05 ~ 2024.03.04)

This project detects anomalies in 2D data using PyTorch for model training and Flutter for a cross-platform application. Key features include 📊 pre-trained models, a 📱 Flutter mobile app that shows heat maps, a 🌐 Flask server backend, and a 🖥️ Tkinter desktop app.

Anomaly detection autoencoder model with a focus on industrial images inspection.

Data loader for the MVTec dataset, a comprehensive real-world dataset for Unsupervised Anomaly Detection

Thesis project about Visual Anomaly Detection based on Self Supervised Learning. The model identifies anomalies from information acquired during training, where normality and anomaly patterns are built using syntetic data

Using SPADE for anomaly detection on MVTEC LOCO AD dataset

Repository for the Exposing Outlier Exposure paper

The solutions for the dacon competition (1st place).

EfficientNetV2 based PaDiM

PatchCore method for Industrial Anomaly Detection + CLIP

This is an unofficial implementation of ' Anomaly localization by modeling perceptual features'

🪥 Unofficial re-implementation of Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation

Semi-Orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation

🐬 Re-implementation of PaDiM and code for the article "Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images"