Improved Out-of-domain Detection in VAE Latent Spaces with Boundary-driven Regularisation

Abstract

In out-of-domain (OOD) detection tasks, encoding the actual data into a suitable latent space could be beneficial since it may facilitate measurement of the spatial relationship between in-domain (IND) and OOD data. However, any such mapping of data to a latent space carries the risk that some OOD points may be mapped to in-domain regions. To address this drawback we propose a novel method that spatially separates these two domains in the latent space. It first geometrically defines the boundary of IND in the latent space and then forces some enumerated OOD data (known as surrogate OOD) to fit that boundary. This then helps the encoder to map OOD to the surrounding area of IND, consequently reducing any overlap. Following this, accurate OOD detection is achieved by a dedicated detector distinguishing IND and its boundary. We illustrate the effects of the proposed method on synthetic data and validated it over both grey-scale and RGB image datasets.