{"url":"/dataset/visa","name":"VisA","full_name":"Visual Anomaly Dataset","description_markdown":"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.","description_withheld":null,"homepage":"https://amazon-visual-anomaly.s3.us-west-2.amazonaws.com/VisA_20220922.tar","introduced_date":"2022-07-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/spot-the-difference-self-supervised-pre","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","first_author":"Yang Zou","url":null},"license":null,"modalities":[],"tasks":[{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"},{"name":"Anomaly Classification","url":"/task/anomaly-classification","datasets_with_task":"/datasets/task/anomaly-classification"},{"name":"zero-shot anomaly detection","url":"/task/zero-shot-anomaly-detection","datasets_with_task":"/datasets/task/zero-shot-anomaly-detection"},{"name":"Multi-class Anomaly Detection","url":"/task/multi-class-anomaly-detection","datasets_with_task":"/datasets/task/multi-class-anomaly-detection"}],"languages":[],"variants":["VisA"],"data_loaders":[{"repo":"https://github.com/openvinotoolkit/anomalib","url":"https://github.com/openvinotoolkit/anomalib","frameworks":["pytorch"]}],"num_papers_in_archive":86,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/anomaly-detection-on-visa","task":"Anomaly Detection","dataset_variant":"VisA","rows":50,"metrics":["Detection AUROC","Segmentation AUPRO (until 30% FPR)","F1-Score","Segmentation AUPRO","Segmentation AUROC"],"first_row_in_archive_order":{"model":"UniNet","paper":"/paper/uninet-a-contrastive-learning-guided-unified","metrics":{"Detection AUROC":"99.8","Segmentation AUPRO":"93.9","Segmentation AUPRO (until 30% FPR)":"93.9","Segmentation AUROC":"98.8"},"code_links":[{"title":"pangdatangtt/UniNet","url":"https://github.com/pangdatangtt/UniNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/anomaly-classification-on-visa","task":"Anomaly Classification","dataset_variant":"VisA","rows":1,"metrics":["Detection AUROC"],"first_row_in_archive_order":{"model":"APRIL-GAN","paper":"/paper/a-zero-few-shot-anomaly-classification-and","metrics":{"Detection AUROC":"78.0"},"code_links":[{"title":"bychelsea/vand-april-gan","url":"https://github.com/bychelsea/vand-april-gan"},{"title":"hq-deng/AnoVL","url":"https://github.com/hq-deng/AnoVL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-class-anomaly-detection-on-visa","task":"Multi-class Anomaly Detection","dataset_variant":"VisA","rows":0,"metrics":["Detection AUROC"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/center-aware-residual-anomaly-synthesis-for","title":"Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection","date":"2025-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/exploring-intrinsic-normal-prototypes-within","title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","date":"2025-03-04","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/uninet-a-contrastive-learning-guided-unified","title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","date":"2025-02-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/progressive-boundary-guided-anomaly-synthesis","title":"Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection","date":"2024-12-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unlocking-the-potential-of-reverse","title":"Unlocking the Potential of Reverse Distillation for Anomaly Detection","date":"2024-12-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/2408-03143","title":"SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection","date":"2024-08-06","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/adaclip-adapting-clip-with-hybrid-learnable","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","date":"2024-07-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":19,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vcp-clip-a-visual-context-prompting-model-for","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","date":"2024-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-unified-anomaly-synthesis-strategy-with","title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","date":"2024-07-12","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/glad-towards-better-reconstruction-with","title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","date":"2024-06-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":10,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dinomaly-the-less-is-more-philosophy-in-multi","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","date":"2024-05-23","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":9,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/anomalydino-boosting-patch-based-few-shot","title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","date":"2024-05-23","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":9,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/realnet-a-feature-selection-network-with","title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","date":"2024-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":9,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/musc-zero-shot-industrial-anomaly","title":"MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images","date":"2024-01-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/d3ad-dynamic-denoising-diffusion","title":"Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection","date":"2024-01-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transfusion-a-transparency-based-diffusion","title":"TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection","date":"2023-11-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/anomalyclip-object-agnostic-prompt-learning","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","date":"2023-10-29","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":32,"samples_ran":14,"samples_unverified":18,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fair-frequency-aware-image-restoration-for","title":"FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection","date":"2023-09-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-zero-few-shot-anomaly-classification-and","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","date":"2023-05-27","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":4,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/anomaly-detection-with-conditioned-denoising","title":"Anomaly Detection with Conditioned Denoising Diffusion Models","date":"2023-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/segment-any-anomaly-without-training-via","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","date":"2023-05-18","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hard-nominal-example-aware-template-mutual","title":"Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection","date":"2023-03-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/winclip-zero-few-shot-anomaly-classification","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","date":"2023-03-26","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":5,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficientad-accurate-visual-anomaly-detection","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","date":"2023-03-25","rows_on_this_dataset":2,"code_links":33,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":35,"samples_ran":1,"samples_unverified":34,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/diffusionad-denoising-diffusion-for-anomaly","title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","date":"2023-03-15","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/reconstruction-from-edge-image-combined-with","title":"Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection","date":"2022-10-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/asymmetric-student-teacher-networks-for","title":"Asymmetric Student-Teacher Networks for Industrial Anomaly Detection","date":"2022-10-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dsr-a-dual-subspace-re-projection-network-for","title":"DSR -- A dual subspace re-projection network for surface anomaly detection","date":"2022-08-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spot-the-difference-self-supervised-pre","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","date":"2022-07-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/anoddpm-anomaly-detection-with-denoising","title":"AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise","date":"2022-06-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cfa-coupled-hypersphere-based-feature","title":"CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization","date":"2022-06-09","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/beyond-dents-and-scratches-logical","title":"Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization","date":"2022-02-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/anomaly-detection-via-reverse-distillation","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","date":"2022-01-26","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":14,"samples_unverified":4,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fastflow-unsupervised-anomaly-detection-and","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","date":"2021-11-15","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/draem-a-discriminatively-trained","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","date":"2021-08-17","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cflow-ad-real-time-unsupervised-anomaly","title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","date":"2021-07-27","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":3,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/student-teacher-feature-pyramid-matching-for","title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","date":"2021-03-07","rows_on_this_dataset":1,"code_links":10,"syntology":null},{"paper":"/paper/padim-a-patch-distribution-modeling-framework","title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","date":"2020-11-17","rows_on_this_dataset":1,"code_links":26,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/anomaly-localization-by-modeling-perceptual","title":"Anomaly localization by modeling perceptual features","date":"2020-08-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sub-image-anomaly-detection-with-deep-pyramid","title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","date":"2020-05-05","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/uninformed-students-student-teacher-anomaly","title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","date":"2019-11-06","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":23,"samples_harvested":258,"samples_ran":130,"samples_unverified":128,"pointer_only_for_licence":21,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}