Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

VisA

Visual Anomaly Dataset

Introduced 2022-07-28

The VisA dataset contains 12 subsets corresponding to 12 different objects as shown in the above figure. There are 10,821 images with 9,621 normal and 1,200 anomalous samples. Four subsets are different types of printed circuit boards (PCB) with relatively complex structures containing transistors, capacitors, chips, etc. For the case of multiple instances in a view, we collect four subsets: Capsules, Candles, Macaroni1 and Macaroni2. Instances in Capsules and Macaroni2 largely differ in locations and poses. Moreover, we collect four subsets including Cashew, Chewing gum, Fryum and Pipe fryum, where objects are roughly aligned. The anomalous images contain various flaws, including surface defects such as scratches, dents, color spots or crack, and structural defects like misplacement or missing parts.

Benchmarks

2D Classification/Detection AUROC Anomaly Classification/Detection AUROC Anomaly Detection/Detection AUROC Anomaly Detection/Segmentation AUPRO (until 30% FPR)Anomaly Detection/F1-Score Anomaly Detection/Segmentation AUPRO Anomaly Detection/Segmentation AUROC

Related Benchmarks

ViSal/16k/Average MAE ViSal/16k/S-Measure ViSal/16k/max E-measure ViSal/2D Classification/Average MAE ViSal/2D Classification/S-Measure ViSal/2D Classification/max E-measure ViSal/2D Object Detection/Average MAE ViSal/2D Object Detection/S-Measure ViSal/2D Object Detection/max E-measure ViSal/3D/Average MAE ViSal/3D/S-Measure ViSal/3D/max E-measure ViSal/Object Detection/Average MAE ViSal/Object Detection/S-Measure ViSal/Object Detection/max E-measure ViSal/RGB Salient Object Detection/Average MAE ViSal/RGB Salient Object Detection/S-Measure ViSal/RGB Salient Object Detection/max E-measure ViSal/Video/Average MAE ViSal/Video/S-Measure ViSal/Video/max E-measure ViSal/Video Object Segmentation/Average MAE ViSal/Video Object Segmentation/S-Measure ViSal/Video Object Segmentation/max E-measure VisA-AC/2D Classification/Accuracy(%)VisA-AC/Anomaly Classification/Accuracy(%)VisA-AC/Anomaly Detection/Accuracy(%)

Statistics

Papers: 86
Benchmarks: 7

Links

Tasks

2D Classification Anomaly Classification Anomaly Detection Multi-class Anomaly Detection zero-shot anomaly detection