paper-with-me

홈 › Papers

Deep Anomaly Detection Using Geometric Transformations

2018-05-28 · NeurIPS 2018 12 · Izhak Golan, Ran El-Yaniv

We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a "normal" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is to train a multi-class model to discriminate between dozens of geometric transformations applied on all the given images. The auxiliary expertise learned by the model generates feature detectors that effectively identify, at test time, anomalous images based on the softmax activation statistics of the model when applied on transformed images. We present extensive experiments using the proposed detector, which indicate that our algorithm improves state-of-the-art methods by a wide margin.

📄 PDF Abstract BibTeX arXiv:1805.10917

Code (3)

izikgo/AnomalyDetectionTransformations 공식 구현 tf
khw11044/MY_GOAD pytorch
ninatu/anomaly_detection pytorch

Tasks

Anomaly Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Self-Supervised Out-of-Distribution Detection in Brain CT Scans

2020-11-10 · Abinav Ravi Venkatakrishnan, Seong Tae Kim, Rami Eisawy, Franz Pfister 외

Medical imaging data suffers from the limited availability of annotation because annotating 3D medical data is a time-consuming and expensive task. Moreover, even if the annotation is available, supervised learning-based…

Anomaly DetectionOut-of-Distribution DetectionSelf-Supervised Learning

SGANet: Semantic and Geometric Alignment for Multimodal Multi-view Anomaly Detection

2026-04-07 · Letian Bai, Chengyu Tao, Juan Du arxiv

Multi-view anomaly detection aims to identify surface defects on complex objects using observations captured from multiple viewpoints. However, existing unsupervised methods often suffer from feature inconsistency arisin…

Anomaly Detection

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection

2025-10-19 · Yuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang 외 arxiv

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent …

Representation Learning3D Anomaly Detection

Unsupervised Anomaly Detection From Semantic Similarity Scores

2020-12-01 · Nima Rafiee, Rahil Gholamipoor, Markus Kollmann

Classifying samples as in-distribution or out-of-distribution (OOD) is a challenging problem of anomaly detection and a strong test of the generalisation power for models of the in-distribution. In this paper, we present…

Anomaly DetectionOut-of-Distribution DetectionSemantic SimilaritySemantic Textual Similarity+1

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

2021-03-30 · Chen Qiu, Timo Pfrommer, Marius Kloft, Stephan Mandt 외

Data transformations (e.g. rotations, reflections, and cropping) play an important role in self-supervised learning. Typically, images are transformed into different views, and neural networks trained on tasks involving …

Anomaly DetectionSelf-Supervised LearningTime SeriesTime Series Analysis