Overparametrization of HyperNetworks at Fixed FLOP-Count Enables Fast Neural Image Enhancement
Deep convolutional neural networks can enhance images taken with small mobile camera sensors and excel at tasks like demoisaicing, denoising and super-resolution. However, for practical use on mobile devices these networks often require too many FLOPs and reducing the FLOPs of a convolution layer, also reduces its parameter count. This is problematic in view of the recent finding that heavily over-parameterized neural networks are often the ones that generalize best. In this paper we propose to use HyperNetworks to break the fixed ratio of FLOPs to parameters of standard convolutions. This allows us to exceed previous state-of-the-art architectures in SSIM and MS-SSIM on the Zurich RAW- to-DSLR (ZRR) data-set at > 10x reduced FLOP-count. On ZRR we further observe generalization curves consistent with 'double-descent' behavior at fixed FLOP-count, in the large image limit. Finally we demonstrate the same technique can be applied to an existing network (VDN) to reduce its computational cost while maintaining fidelity on the Smartphone Image Denoising Dataset (SIDD). Code for key functions is given in the appendix.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage DenoisingImage EnhancementMS-SSIMSSIMSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Universal Hypernetworks for Arbitrary Models
Conventional hypernetworks are typically engineered around a specific base-model parameterization, so changing the target architecture often entails redesigning the hypernetwork and retraining it from scratch. We introdu…
Multi-Task LearningContinual Model-Based Reinforcement Learning with Hypernetworks
Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynamics model. In many instances of MBRL and MPC, this model is assumed to be stat…
Continual LearningmodelModel-based Reinforcement LearningModel Predictive Control+3Kernel Regression of Multi-Way Data via Tensor Trains with Hadamard Overparametrization: The Dynamic Graph Flow Case
A regression-based framework for interpretable multi-way data imputation, termed Kernel Regression via Tensor Trains with Hadamard overparametrization (KReTTaH), is introduced. KReTTaH adopts a nonparametric formulation …
The Lattice Overparametrization Paradigm for the Machine Learning of Lattice Operators
The machine learning of lattice operators has three possible bottlenecks. From a statistical standpoint, it is necessary to design a constrained class of operators based on prior information with low bias, and low comple…
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although hypernetworks are typ…
Test-time Adaptation