Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis

Liu, K; Liu, F; Wang, H; Ma, N; Bu, J; Han, B

Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis

Liu, K Liu, F

Wang, H Ma, N Bu, J Han, B

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2024, 00, pp. 5451-5460
Issue Date:: 2024-01-15

Closed Access

	Filename	Description	Size
	1722431.pdf	Published version	10.75 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, K
dc.contributor.author	Liu, F https://orcid.org/0000-0002-5005-9129
dc.contributor.author	Wang, H
dc.contributor.author	Ma, N
dc.contributor.author	Bu, J
dc.contributor.author	Han, B
dc.date	2023-10-01
dc.date.accessioned	2024-05-13T04:35:32Z
dc.date.available	2024-05-13T04:35:32Z
dc.date.issued	2024-01-15
dc.identifier.citation	2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2024, 00, pp. 5451-5460
dc.identifier.isbn	979-8-3503-0719-1
dc.identifier.issn	1550-5499
dc.identifier.uri	http://hdl.handle.net/10453/178929
dc.description.abstract	Implicit neural representations INRs aim to learn a continuous function i e a neural network to represent an image where the input and output of the function are pixel coordinates and RGB Gray values respectively However images tend to consist of many objects whose colors are not perfectly consistent resulting in the challenge that image is actually a discontinuous piecewise function and cannot be well estimated by a continuous function In this paper we empirically investigate that if a neural network is enforced to fit a discontinuous piecewise function to reach a fixed small error the time costs will increase exponentially with respect to the boundaries in the spatial domain of the target signal We name this phenomenon the exponential increase hypothesis Under the exponential increase hypothesis learning INRs for images with many objects will converge very slowly To address this issue we first prove that partitioning a complex signal into several sub regions and utilizing piecewise INRs to fit that signal can significantly speed up the convergence Based on this fact we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction one for learning INRs and the other for learning to learn INRs In both cases we partition an image into different sub regions and dedicate smaller networks for each part In addition we further propose two partition rules based on regular grids and semantic segmentation maps respectively Extensive experiments validate the effectiveness of the proposed partitioning methods in terms of learning INR for a single image ordinary learning framework and the learning to learn framework Code is released here
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2023 IEEE/CVF International Conference on Computer Vision (ICCV)
dc.relation.ispartof	2023 IEEE/CVF International Conference on Computer Vision
dc.relation.isbasedon	10.1109/iccv51070.2023.00504
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Paris, France
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2024-05-13T04:35:21Z
pubs.finish-date	2023-10-06
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2023-10-01
pubs.volume	00
dc.location	Piscataway, USA

Abstract:

Implicit neural representations INRs aim to learn a continuous function i e a neural network to represent an image where the input and output of the function are pixel coordinates and RGB Gray values respectively However images tend to consist of many objects whose colors are not perfectly consistent resulting in the challenge that image is actually a discontinuous piecewise function and cannot be well estimated by a continuous function In this paper we empirically investigate that if a neural network is enforced to fit a discontinuous piecewise function to reach a fixed small error the time costs will increase exponentially with respect to the boundaries in the spatial domain of the target signal We name this phenomenon the exponential increase hypothesis Under the exponential increase hypothesis learning INRs for images with many objects will converge very slowly To address this issue we first prove that partitioning a complex signal into several sub regions and utilizing piecewise INRs to fit that signal can significantly speed up the convergence Based on this fact we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction one for learning INRs and the other for learning to learn INRs In both cases we partition an image into different sub regions and dedicate smaller networks for each part In addition we further propose two partition rules based on regular grids and semantic segmentation maps respectively Extensive experiments validate the effectiveness of the proposed partitioning methods in terms of learning INR for a single image ordinary learning framework and the learning to learn framework Code is released here

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/178929