Poster
in
Workshop: Spurious correlations, Invariance, and Stability (SCIS)
Unsupervised Causal Generative Understanding of Images
Titas Anciukevičius · Patrick Fox-Roberts · Edward Rosten · Paul Henderson
Keywords: [ generative model ] [ Causality ] [ Unsupervised Learning ] [ Computer Vision ] [ neural rendering ]
We present a novel causal generative model for unsupervised object-centric 3D scene understanding that generalizes robustly to out-of-distribution images.This model is trained to reconstruct multi-view images via a latent representation describing the shapes, colours and positions of the 3D objects they show.We then propose an inference algorithm that can infer this latent representation given a single out-of-distribution image as input.We conduct extensive experiments applying our approach to test datasets that have zero probability under the training distribution.Our approach significantly out-performs baselines that do not capture the true causal image generation process.