Stars
[CSCWD] Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead.
Paper list for industrial image anomaly synthesis methods.
Pipeline training and inference Anomalib models UI in Anomaly Detection
Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。
用于在给定 Python 源文件与行号时，定位该行所处的类/函数作用域，并输出其模块的完全限定名（Fully Qualified Name，FQName）、类名、函数名、相对路径位置以及该行内容。
Reference PyTorch implementation and models for DINOv3
AAAI-2025: The largest and first anomaly detection dataset dedicated to 3C product quality control
[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
[ECCV 2024 Oral] The official implementation of "CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model".
[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"
Paper and implementation of UNet-related model.
BMAD hold a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) license
Recent papers about anomaly detection in medical images.
anomaly detection by one-class SVM
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Project for <SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation> (ECCV 2022)
Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)
Code for ECCV 2022 paper "Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization".
An Examination of the Compositionality of Large Generative Vision-Language Models
[CVPR 2025] Official Implementation of "Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection". The first multi-class UAD model that can compete with single-class SOTAs
The official implementation of the paper DADF for industrial VAD
Implementation for paper:"Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection"
Source code and data set for the paper"Few-Shot Unseen Defect Segmentation for Polycrystalline Silicon Panels with An Interpretable Dual Subspace Attention Variational Learning Framework"
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
Using Hough Transform to detect straight lane lines