ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Implicit Neural Representation, Coordinate Network, Multi-resolution, Efficient Inference
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose the Activation-Sharing Multi-Resolution (ASMR) coordinate network to enhance the inference efficiency of INRs. ASMR achieves high-quality reconstruction results with a low MAC count in various signal-fitting tasks.
Abstract: Coordinate network or implicit neural representation (INR) is a fast-emerging method for encoding natural signals (such as images and videos) with the benefits of a compact neural representation. While numerous methods have been proposed to increase the encoding capabilities of an INR, an often overlooked aspect is the inference efficiency, usually measured in multiply-accumulate (MAC) count. This is particularly critical in use cases where inference bandwidth is greatly limited by hardware constraints. To this end, we propose the Activation-Sharing Multi-Resolution (ASMR) coordinate network that combines multi-resolution coordinate decomposition with hierarchical modulations. Specifically, an ASMR model enables the sharing of activations across grids of the data. This largely decouples its inference cost from its depth which is directly correlated to its reconstruction capability, and renders a near $O(1)$ inference complexity irrespective of the number of layers. Experiments show that ASMR can reduce the MAC of a vanilla SIREN model by up to 500$\times$ while achieving an even higher reconstruction quality than its SIREN baseline.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: representation learning for computer vision, audio, language, and other modalities
Submission Number: 7291
Loading