Official implementation of CVPR 2024 PromptAD: Learning Prompts with Only Normal Samples for Few-Shot Anomaly Detection

This repository is the official implementation of "Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection"

The official PyTorch implementation of the IEEE/CVF International Conference on Computer Vision (ICCV) '23 paper Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detec…

Codebase for Patched Diffusion Models for Unsupervised Anomaly Detection .

Offical implementation of "Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series" (ICLR 2022)

PyTorch implementation of "Drift doesn't Matter: Dynamic Decomposition with Dffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection" (NeurIPS 2023)

[AAAI 2025] Official Implementation of "HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting"

Learning Diffusion Models for Multi-View Anomaly Detection [ECCV2024]

[ICIP 2023] Exploring Diffusion Models For Unsupervised Video Anomaly Detection

KDD 2019: Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network

RNN based Time-series Anomaly detector model implemented in Pytorch.

[ICLR 2024] Official Implementation of "Diffusion-TS: Interpretable Diffusion for General Time Series Generation"

Implementations, Pre-training Code and Datasets of Large Time-Series Models

DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences, Neuron Visualisations, and Visual Counterfactual Explanations

Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation (ECCV 2024 ORAL)

Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder

Official Code for the ACCV 2022 paper Diffusion Models for Counterfactual Explanations

Generate Diverse Counterfactual Explanations for any machine learning model.

This repository provides a modular and configurable framework for generating counterfactual explanations in Graph Neural Networks (GNNs) using node feature and structural perturbations.

This repository contains the source code for the method described in the following publication: Anomaly Attribution of Multivariate Time-Series using Counterfactual Reasoning

CGAD (Causal Graph for Multivariate Time Series Anomaly Detection) [ACM TIST'25]

[ECCV 2024] Official Implementation and Dataset Release for "A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization"