LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
Author(s)
Wu, H
Chen, G
Dragotti, PL
Gündüz, D
Type
Conference Paper
Abstract
We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted image compression, achieving rate-distortion (RD) performance comparable to trained networks. This hypothesis leads to a new paradigm for image compression by encoding image statistics into the network substructure. Building on this hypothesis, we propose LotteryCodec, which overfits a binary mask to an individual image, leveraging an overparameterized and randomly initialized network shared by the encoder and the decoder. To address over-parameterization challenges and streamline subnetwork search, we develop a rewind modulation mechanism that improves the RD performance. LotteryCodec outperforms VTM and sets a new state-of-the-art in single-image compression. LotteryCodec also enables adaptive decoding complexity through adjustable mask ratios, offering flexible compression solutions for diverse device constraints and application requirements. Project page: https://eedavidwu. github.io/LotteryCodec/
Date Issued
2025-07-13
Date Acceptance
2025-07-01
Citation
Proceedings of Machine Learning Research, 2025, 267, pp.67147-67171
Publisher
ML Research Press
Start Page
67147
End Page
67171
Journal / Book Title
Proceedings of Machine Learning Research
Volume
267
Copyright Statement
Copyright © The authors and PMLR 2026. MLResearchPress.
Source
International Conference on Machine Learning 2025
Publication Status
Published
Start Date
2025-07-13
Finish Date
2025-07-19
Coverage Spatial
Vancouver, Canada