The reviewed record of science sign in
Pith

arxiv: 2301.09479 · v3 · pith:YHYAL3QW · submitted 2023-01-23 · stat.ML · cs.AI· cs.LG

Modality-Agnostic Variational Compression of Implicit Neural Representations

Reviewed by Pithpith:YHYAL3QWopen to challenge →

classification stat.ML cs.AIcs.LG
keywords neuralcompressionrepresentationsdataimplicitlatentmodality-agnosticalgorithm
0
0 comments X
read the original abstract

We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR). Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. This allows the specialisation of a shared INR network to each data item through subnetwork selection. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression. Variational Compression of Implicit Neural Representations (VC-INR) shows improved performance given the same representational capacity pre quantisation while also outperforming previous quantisation schemes used for other INR techniques. Our experiments demonstrate strong results over a large set of diverse modalities using the same algorithm without any modality-specific inductive biases. We show results on images, climate data, 3D shapes and scenes as well as audio and video, introducing VC-INR as the first INR-based method to outperform codecs as well-known and diverse as JPEG 2000, MP3 and AVC/HEVC on their respective modalities.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.