# ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects Source: [ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:47.628Z Authors: Ricky Ma Published: 2021-04-26T01:13:28.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()