Machine Learning & Applications (MaLA)

InCTRL

Official implementation of CVPR'24 paper 'Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts'.

TAM-master

Official implementation of NeurIPS'23 paper "Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection"

ADShift

Official PyTorch implementation of the ICCV'23 paper “Anomaly Detection under Distribution Shift”

AHL

Official implementation of CVPR'24 paper 'Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection'.

SIC-CADS

Code Implementation of "Simple Image-level Classification Improves Open-vocabulary Object Detection" (AAAI'24)

PReNet

Official implementation of KDD'23 paper "Deep Weakly-supervised Anomaly Detection"

NegPrompt

The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"

COCL

Official implementation for "Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning" (AAAI'24)

out-of-distribution-detection-resources

Top-tier conference papers on out-of-distribution detection

WinCLIP

Implementation of CVPR'23 paper "WinCLIP: Zero-/few-shot anomaly classification and segmentation". It successfully reproduces the same zero-/few-shot AD performance as that in the original paper.

GGAD

This code is for the paper titled with Generative Semi-supervised Graph Anomaly Detection

ADRepository-Anomaly-detection-datasets

Popular real-world datasets for anomaly detection on tabular data, graph data, image data, time series data, and video data

AUGCL

Official code for TNNLS paper "Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning"

AnomalyCLIP

Official implementation for paper "Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection" (ICLR 2024)

Awesome-Deep-Graph-Anomaly-Detection

A repository for resources of deep learning-based graph anomaly detection.

DevNet

Official implementation of KDD'19 paper "Deep Anomaly Detection with Deviation Networks"

rosas

official implementation of RoSAS: Deep Semi-supervised Anomaly Detection with Contamination-resilient Continuous Supervision

VadCLIP

VadCLIP official Pytorch implementation "VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection" in AAAI 2024.

.github

ACT

The official PyTorch implementation of Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment (AAAI2023, to appear).

Glocal

[CVPR 2023] Glocal Energy-based Learning for Few-Shot Open-Set Recognition

PEBAL

[ECCV'22 Oral] Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes. Dealing with out-of-distribution detection or open-set recognition in semantic segmentation.

RPL

Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

weakly-polyp

[MICCAI'22] Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection.

ADer

ADer is an open source visual anomaly detection toolbox based on PyTorch, which supports multiple popular AD datasets and approaches.

ASE

Source code of "Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds". This repository focuses on the problem of Zero-Shot Open-Set Recognition (ZS-OSR), which aims to accurately classify samples from unseen classes while being able to reject samples from unknown classes during inference.

deep-iforest

Implementation of "Deep Isolation Forest for Anomaly Detection"

HimNet

Code for ECMLPKDD23 paper "Graph-level Anomaly Detection via Hierarchical Memory Networks" (HimNet)

HRGCN

Code Repository for Paper "HRGCN: Heterogeneous Graph-level Anomaly Detection with Hierarchical Relation-augmented Graph Neural Networks"

mepu-owod

Code Implementation of "Unsupervised Recognition of Unknown Objects for Open-World Object Detection"