Official Pytorch Implementation for paper: TAB: Text-Align Anomaly Backbone Model for Industrial Inspection Tasks

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

Mamba SSM architecture

Official implementation for AnomalyCLIP (ICLR 2024)

A curated list of prompt-based paper in computer vision and vision-language learning.

ICCV 2023: CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

[AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

The official code for "MSFlow: Multi-Scale Normalizing Flows for Unsupervised Anomaly Detection"

REB：Reducing Biases in Representation for Industrial Anomaly Detection

This is an official implementation of the paper : "Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval" (Accepted by IEEE TIP)

EfficientNetV2 based PaDiM

[ICCV'23 Main Track, WECIA'23 Oral] Official repository of paper titled "Self-regulating Prompts: Foundational Model Adaptation without Forgetting".

Meta-Transformer for Unified Multimodal Learning

Anomaly detection on images using features from pretrained neural networks.

[IEEE RA-L 2024] PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly (Defect) Detection and Segmentation

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

Vanilla torch and timm industrial knn-based anomaly detection for images.

[CVPR 2023] Unofficial PyTorch implementation for CVPR2023 paper, Prototypical Residual Networks for Anomaly Detection and Localization.

Image anomaly detection benchmark in industrial manufacturing

[CVPR 2023 Workshop] VAND Challenge: 1st Place on Zero-shot AD and 4th Place on Few-shot AD

Unofficial pytorch implementation of Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection

An open source implementation of CLIP.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".