Unsupervised detection of mouse behavioural anomalies using two-stream convolutional autoencoders
This work addresses anomaly detection in behavioral neuroscience for researchers, but it is incremental as it adapts existing autoencoder architectures to a specific domain.
The paper tackled unsupervised anomaly detection in mouse behavior videos using two-stream convolutional autoencoders, achieving performance comparable to state-of-the-art methods on a public dataset and the CUHK Avenue dataset.
This paper explores the application of unsupervised learning to detecting anomalies in mouse video data. The two models presented in this paper are a dual-stream, 3D convolutional autoencoder (with residual connections) and a dual-stream, 2D convolutional autoencoder. The publicly available dataset used here contains twelve videos of single home-caged mice alongside frame-level annotations. Under the pretext that the autoencoder only sees normal events, the video data was handcrafted to treat each behaviour as a pseudo-anomaly thereby eliminating them from the others during training. The results are presented for one conspicuous behaviour (hang) and one inconspicuous behaviour (groom). The performance of these models is compared to a single stream autoencoder and a supervised learning model, which are both based on the custom CAE. Both models are also tested on the CUHK Avenue dataset were found to perform as well as some state-of-the-art architectures.