D'OH: Decoder-Only random Hypernetworks for Implicit Neural Representations

arXiv:2403.19163v1 Announce Type: new
Abstract: Deep implicit functions have been found to be an effective tool for efficiently encoding all manner of natural signals. Their attractiveness stems from their ability to compactly represent signals with little to no off-line training data. Instead, they leverage the implicit bias of deep networks to decouple hidden redundancies within the signal. In this paper, we explore the hypothesis that additional compression can be achieved by leveraging the redundancies that exist between layers. We propose …

abstract arxiv bias cs.cv cs.lg data decoder encoding found functions implicit neural representations line natural networks random tool training training data type