ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects

2021-04-26 · Ricky Ma

This paper presents a novel framework for unsupervised anomaly detection on masked objects called ODDObjects, which stands for Out-of-Distribution Detection on Objects. ODDObjects is designed to detect anomalies of various categories using unsupervised autoencoders trained on COCO-style datasets. The method utilizes autoencoder-based image reconstruction, where high reconstruction error indicates the possibility of an anomaly. The framework extends previous work on anomaly detection with autoencoders, comparing state-of-the-art models trained on object recognition datasets. Various model architectures were compared, and experimental results show that memory-augmented deep convolutional autoencoders perform the best at detecting out-of-distribution objects.

📄 PDF Abstract BibTeX arXiv:2104.12300

Code (1)

ricky-ma/ODDObjects 공식 구현 tf

Tasks

Anomaly Detection Image Reconstruction Object Recognition Out-of-Distribution Detection Unsupervised Anomaly Detection

Stack of discriminative autoencoders for multiclass anomaly detection in endoscopy images

2021-03-15 · Mohammad Reza Mohebbian, Khan A. Wahid, Paul Babyn

Wireless Capsule Endoscopy (WCE) helps physicians examine the gastrointestinal (GI) tract noninvasively. There are few studies that address pathological assessment of endoscopy images in multiclass classification and mos…

Anomaly Detection Clustering General Classification

Robust Anomaly Map Assisted Multiple Defect Detection with Supervised Classification Techniques

2022-12-19 · Jože M. Rožanec, Patrik Zajec, Spyros Theodoropoulos, Erik Koehorst 외

Industry 4.0 aims to optimize the manufacturing environment by leveraging new technological advances, such as new sensing capabilities and artificial intelligence. The DRAEM technique has shown state-of-the-art performan…

Classification Defect Detection

A Novel Unified Lightweight Temporal-Spatial Transformer Approach for Intrusion Detection in Drone Networks

2025-10-03 · Tarun Kumar Biswas, Ashrafun Zannat, Waqas Ishtiaq, Md. Alamgir Hossain arxiv

The growing integration of drones across commercial, industrial, and civilian domains has introduced significant cybersecurity challenges, particularly due to the susceptibility of drone networks to a wide range of cyber…

Intrusion Detection Anomaly Detection

Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencoder

2023-04-07 · Mana Masuda, Ryo Hachiuma, Ryo Fujii, Hideo Saito 외

In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represen…

Anomaly Detection Unsupervised Anomaly Detection

UaiNets: From Unsupervised to Active Deep Anomaly Detection

2019-05-01 · ICLR 2019 5 · Tiago Pimentel, Marianne Monteiro, Juliano Viana, Adriano Veloso 외

This work presents a method for active anomaly detection which can be built upon existing deep learning solutions for unsupervised anomaly detection. We show that a prior needs to be assumed on what the anomalies are, in…

Anomaly Detection Deep Learning Unsupervised Anomaly Detection