DC Field | Value | Language |
---|---|---|
dc.contributor.author | LEE, JAEHO | - |
dc.contributor.author | Schwarz, Jonathan Richard | - |
dc.contributor.author | Tack, Jihoon | - |
dc.contributor.author | Teh, Yee Whye | - |
dc.contributor.author | Shin, Jinwoo | - |
dc.date.accessioned | 2024-03-06T06:04:38Z | - |
dc.date.available | 2024-03-06T06:04:38Z | - |
dc.date.created | 2024-03-06 | - |
dc.date.issued | 2023-07-23 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/121637 | - |
dc.description.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. | - |
dc.language | English | - |
dc.publisher | ML Research Press | - |
dc.relation.isPartOf | 40th International Conference on Machine Learning, ICML 2023 | - |
dc.relation.isPartOf | Proceedings of Machine Learning Research | - |
dc.title | Modality-Agnostic Variational Compression of Implicit Neural Representations | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 40th International Conference on Machine Learning, ICML 2023, pp.30342 - 30364 | - |
dc.citation.conferenceDate | 2023-07-23 | - |
dc.citation.conferencePlace | US | - |
dc.citation.endPage | 30364 | - |
dc.citation.startPage | 30342 | - |
dc.citation.title | 40th International Conference on Machine Learning, ICML 2023 | - |
dc.contributor.affiliatedAuthor | LEE, JAEHO | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.