ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects
This work addresses anomaly detection for masked objects in computer vision, but it is incremental as it extends prior autoencoder methods.
The paper tackles unsupervised anomaly detection on masked objects by proposing the ODDObjects framework, which uses autoencoder-based reconstruction error, and finds that memory-augmented deep convolutional autoencoders achieve the best performance.
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.