Measuring hallucination in disentangled representations

Hamed Benazha, Stéphane Ayache, Hachem Kadri, Thierry Artières

Abstract: Disentanglement is a key challenge in representation learning as it may enable several downstream tasks including edition operation at a high semantic level or privacy-preserving applications. While much effort has been put into the design of disentanglement methods and on how to evaluate their disentanglement performance no real studies put in evidence nor proposed to measure the hallucination that may occur in such disentangled representation spaces. This study focuses on characterizing, measuring and investigating hallucination in representation space learnt by state-of-the-art disentanglement methods.