Residual Quantization with Implicit Neural Codebooks

1 code implementation • 26 Jan 2024 • Iris Huijben, Matthijs Douze, Matthew Muckley, Ruud Van Sloun, Jakob Verbeek

In this paper, we propose QINCo, a neural RQ variant which predicts specialized codebooks per vector using a neural network that is conditioned on the approximation of the vector from previous steps.

Data Compression Quantization