Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection

Horwitz, Eliahu; Hoshen, Yedid

doi:10.1109/cvprw59228.2023.00298

Cited by 12 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the release of MVTec 3D-AD [6] dataset, several papers have focused on anomaly detection in 3D industrial images. Bergmann and Sattlegger [150] introduce a teacherstudent model for 3D anomaly detection. The teacher network is trained to acquire general local geometric descriptors by recreating local receptive fields.…”

Section: D Anomaly Detectionmentioning

confidence: 99%

Deep Industrial Image Anomaly Detection: A Survey

Liu,

Xie,

Wang

et al. 2024

Mach. Intell. Res.

View full text Add to dashboard Cite

The recent rapid development of deep learning has laid a milestone in industrial image anomaly detection (IAD). In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets. In addition, we extract the promising setting from industrial manufacturing and review the current IAD approaches under our proposed setting. Moreover, we highlight several opening challenges for image anomaly detection. The merits and downsides of representative network architectures under varying supervision are discussed. Finally, we summarize the research findings and point out future research directions. More resources are available at https://github.com/M-3LAB/awesome-industrial-anomaly-detection.

show abstract

Section: D Anomaly Detectionmentioning

confidence: 99%

Deep Industrial Image Anomaly Detection: A Survey

Liu,

Xie,

Wang

et al. 2024

Mach. Intell. Res.

View full text Add to dashboard Cite

show abstract

“…However, they are hard to directly apply in other image-like domains (e.g. the depth map) (Bergmann et al 2021;Horwitz and Hoshen 2023) or to cover the higher-level anomaly type, logical anomalies (Bergmann et al 2022).…”

Section: Diffusion Processmentioning

confidence: 99%

“…et al 2009) pretrained feature extractor. Nevertheless, such reliance may limit their generalization capabilities in scenarios (Bergmann et al 2022) where ImageNet pretrained features are insufficiently informative, or on other types of image-like data (Bergmann et al 2021;Horwitz and Hoshen 2023). Additionally, some methods have achieved promising results on the MVTec AD (Bergmann et al 2019) without using pretrained feature extractors.…”

Section: Introductionmentioning

confidence: 99%

Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection

Dai,

Wu,

et al. 2024

AAAI

View full text Add to dashboard Cite

Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might limit their adaptability to an increasing set of anomaly detection tasks due to the priors in the selection of auxiliary datasets or the strategy of anomaly simulation. To tackle this challenge, we first introduce a prior-less anomaly generation paradigm and subsequently develop an innovative unsupervised anomaly detection framework named GRAD, grounded in this paradigm. GRAD comprises three essential components: (1) a diffusion model (PatchDiff) to generate contrastive patterns by preserving the local structures while disregarding the global structures present in normal images, (2) a self-supervised reweighting mechanism to handle the challenge of long-tailed and unlabeled contrastive patterns generated by PatchDiff, and (3) a lightweight patch-level detector to efficiently distinguish the normal patterns and reweighted contrastive patterns. The generation results of PatchDiff effectively expose various types of anomaly patterns, e.g. structural and logical anomaly patterns. In addition, extensive experiments on both MVTec AD and MVTec LOCO datasets also support the aforementioned observation and demonstrate that GRAD achieves competitive anomaly detection accuracy and superior inference speed.

show abstract

Rotation invariance and equivariance in 3D deep learning: a survey

Fei,

Deng

2024

Artif Intell Rev

View full text Add to dashboard Cite

Deep neural networks (DNNs) in 3D scenes show a strong capability of extracting high-level semantic features and significantly promote research in the 3D field. 3D shapes and scenes often exhibit complicated transformation symmetries, where rotation is a challenging and necessary subject. To this end, many rotation invariant and equivariant methods have been proposed. In this survey, we systematically organize and comprehensively overview all methods. First, we rewrite the previous definition of rotation invariance and equivariance by classifying them into weak and strong categories. Second, we provide a unified theoretical framework to analyze these methods, especially weak rotation invariant and equivariant ones that are seldom analyzed theoretically. We then divide existing methods into two main categories, i.e., rotation invariant ones and rotation equivariant ones, which are further subclassified in terms of manipulating input ways and basic equivariant block structures, respectively. In each subcategory, their common essence is highlighted, a couple of representative methods are analyzed, and insightful comments on their pros and cons are given. Furthermore, we deliver a general overview of relevant applications and datasets for two popular tasks of 3D semantic understanding and molecule-related. Finally, we provide several open problems and future research directions based on challenges and difficulties in ongoing research.

show abstract

Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection

Cited by 12 publications

References 22 publications

Deep Industrial Image Anomaly Detection: A Survey

Deep Industrial Image Anomaly Detection: A Survey

Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection

Rotation invariance and equivariance in 3D deep learning: a survey

Contact Info

Product

Resources

About