Preprint
Aug 2026
Hide&Seek: Learning to Explain in an End-to-End Differentiable Network
This paper presents Hide&Seek, an end-to-end differentiable model for instance-wise feature selection and prediction under a single objective without information leakage that outperforms existing state-of-the-art models across a range of experiments and is fast to train.
Tal Ellinson, H. Afshar, S. Cripps
· 0 citations