Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
- URL: http://arxiv.org/abs/2405.14325v2
- Date: Wed, 29 May 2024 08:57:31 GMT
- Title: Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
- Authors: Jia Guo, Shuai Lu, Weihang Zhang, Huiqi Li,
- Abstract summary: In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly.
Our proposed Dinomaly achieves impressive image AUROC of 99.6%, 98.7%, and 89.3% on three datasets respectively.
- Score: 29.370142078092375
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images, serving as an alternative to the conventional one-class-one-model setup. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly, which leverages pure Transformer architectures without relying on complex designs, additional modules, or specialized tricks. Given this powerful framework consisted of only Attentions and MLPs, we found four simple components that are essential to multi-class anomaly detection: (1) Foundation Transformers that extracts universal and discriminative features, (2) Noisy Bottleneck where pre-existing Dropouts do all the noise injection tricks, (3) Linear Attention that naturally cannot focus, and (4) Loose Reconstruction that does not force layer-to-layer and point-by-point reconstruction. Extensive experiments are conducted across three popular anomaly detection benchmarks including MVTec-AD, VisA, and the recently released Real-IAD. Our proposed Dinomaly achieves impressive image AUROC of 99.6%, 98.7%, and 89.3% on the three datasets respectively, which is not only superior to state-of-the-art multi-class UAD methods, but also surpasses the most advanced class-separated UAD records.
Related papers
- AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 [16.69402464709241]
We adapt DINOv2 for one-shot and few-shot anomaly detection, with a focus on industrial applications.
Our proposed vision-only approach, AnomalyDINO, is based on patch similarities and enables both image-level anomaly prediction and pixel-level anomaly segmentation.
Despite its simplicity, AnomalyDINO achieves state-of-the-art results in one- and few-shot anomaly detection (e.g., pushing the one-shot performance on MVTec-AD from an AUROC of 93.1% to 96.6%).
arXiv Detail & Related papers (2024-05-23T13:15:13Z) - MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection [1.7234530131333607]
MiniMaxAD is a lightweight autoencoder designed to efficiently compress and memorize extensive information from normal images.
Our model employs a technique that enhances feature diversity, thereby increasing the effective capacity limit of the network.
It also utilizes large kernel convolution to extract highly abstract patterns, which contribute to efficient and compact feature embedding.
arXiv Detail & Related papers (2024-05-16T09:37:54Z) - Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination.
This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field.
Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
arXiv Detail & Related papers (2024-04-16T17:38:26Z) - Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference [67.36605226797887]
We introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD)
By learning the multi-class distributions, the model generates class-aware query embeddings for the transformer decoder.
MINT-AD can project category and position information into a feature embedding space, further supervised by classification and prior probability loss functions.
arXiv Detail & Related papers (2024-03-21T08:08:31Z) - Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets.
We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
arXiv Detail & Related papers (2024-01-06T07:30:41Z) - Generating and Reweighting Dense Contrastive Patterns for Unsupervised
Anomaly Detection [59.34318192698142]
We introduce a prior-less anomaly generation paradigm and develop an innovative unsupervised anomaly detection framework named GRAD.
PatchDiff effectively expose various types of anomaly patterns.
experiments on both MVTec AD and MVTec LOCO datasets also support the aforementioned observation.
arXiv Detail & Related papers (2023-12-26T07:08:06Z) - Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly
Detection [133.93365706990178]
This work studies the recently proposed challenging and practical Multi-class Unsupervised Anomaly Detection (MUAD) task.
It only requires normal images for training while simultaneously testing both normal/anomaly images for multiple classes.
A plain Vision Transformer (ViT) with simple architecture has been shown effective in multiple domains.
arXiv Detail & Related papers (2023-12-12T18:28:59Z) - Anomaly Detection via Multi-Scale Contrasted Memory [3.0170109896527086]
We introduce a new two-stage anomaly detector which memorizes during training multi-scale normal prototypes to compute an anomaly deviation score.
Our model highly improves the state-of-the-art performance on a wide range of object, style and local anomalies with up to 35% error relative improvement on CIFAR-10.
arXiv Detail & Related papers (2022-11-16T16:58:04Z) - SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video
Anomaly Detection [108.57862846523858]
We revisit the self-supervised multi-task learning framework, proposing several updates to the original method.
We modernize the 3D convolutional backbone by introducing multi-head self-attention modules.
In our attempt to further improve the model, we study additional self-supervised learning tasks, such as predicting segmentation maps.
arXiv Detail & Related papers (2022-07-16T19:25:41Z) - A Unified Model for Multi-class Anomaly Detection [33.534990722449066]
UniAD accomplishes anomaly detection for multiple classes with a unified framework.
We evaluate our algorithm on MVTec-AD and CIFAR-10 datasets.
arXiv Detail & Related papers (2022-06-08T06:05:09Z) - Anomaly Detection via Reverse Distillation from One-Class Embedding [2.715884199292287]
We propose a novel T-S model consisting of a teacher encoder and a student decoder.
Instead of receiving raw images directly, the student network takes teacher model's one-class embedding as input.
In addition, we introduce a trainable one-class bottleneck embedding module in our T-S model.
arXiv Detail & Related papers (2022-01-26T01:48:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.