paper-with-me

홈 › Papers

Hyperparameter Optimization in Black-box Image Processing using Differentiable Proxies

2019-04-01 · SIGGRAPH 2019 2019 4 · Ethan Tseng, Felix Yu, Yuting Yang, Fahim Mannan, Karl St. Arnaud, Derek Nowrouzezahrai, Jean-François Lalonde, Felix Heide

Nearly every commodity imaging system we directly interact with, or indirectly rely on, leverages power efficient, application-adjustable black-box hardware image signal processing (ISPs) units, running either in dedicated hardware blocks, or as proprietary software modules on programmable hardware. The configuration parameters of these black-box ISPs often have complex interactions with the output image, and must be adjusted prior to deployment according to application-specific quality and performance metrics. Today, this search is commonly performed manually by "golden eye" experts or algorithm developers leveraging domain expertise. We present a fully automatic system to optimize the parameters of black-box hardware and software image processing pipelines according to any arbitrary (i.e., application-specific) metric. We leverage a differentiable mapping between the configuration space and evaluation metrics, parameterized by a convolutional neural network that we train in an end-to-end fashion with imaging hardware in-the-loop. Unlike prior art, our differentiable proxies allow for high-dimension parameter search with stochastic first-order optimizers, without explicitly modeling any lower-level image processing transformations. As such, we can efficiently optimize black-box image processing pipelines for a variety of imaging applications, reducing application-specific configuration times from months to hours. Our optimization method is fully automatic, even with black-box hardware in the loop. We validate our method on experimental data for real-time display applications, object detection, and extreme low-light imaging. The proposed approach outperforms manual search qualitatively and quantitatively for all domain-specific applications tested. When applied to traditional denoisers, we demonstrate that—just by changing hyperparameters—traditional algorithms can outperform recent deep learning methods by a substantial margin on recent benchmarks.

📄 PDF Abstract BibTeX

Code (1)

Apathetically/ProxyOpt pytorch

Tasks

Hyperparameter OptimizationImage DenoisingImage Quality AssessmentObject Detection

Similar Papers 제목 키워드 기반

Hardware-in-the-Loop End-to-End Optimization of Camera Image Processing Pipelines

2020-06-01 · CVPR 2020 6 · Ali Mosleh, Avinash Sharma, Emmanuel Onzon, Fahim Mannan 외

Commodity imaging systems rely on hardware image signal processing (ISP) pipelines. These low-level pipelines consist of a sequence of processing blocks that, depending on their hyperparameters, reconstruct a color image…

2D Object Detectionobject-detectionObject Detection

A Generalized Framework for Population Based Training

2019-02-05 · Ang Li, Ola Spyra, Sagi Perel, Valentin Dalibard 외

Population Based Training (PBT) is a recent approach that jointly optimizes neural network weights and hyperparameters which periodically copies weights of the best performers and mutates hyperparameters during training.…

Hyperparameter Optimization for Large Language Model Instruction-Tuning

2023-12-01 · Christophe Tribes, Sacha Benarroch-Lelong, Peng Lu, Ivan Kobyzev

The fine-tuning of Large Language Models (LLMs) has enabled them to recently achieve milestones in natural language processing applications. The emergence of ever larger LLMs has paved the way for more efficient fine-tun…

Hyperparameter OptimizationLanguage ModelingLanguage ModellingLarge Language Model+1

Evolutionary Two-Stage Hyperparameter Optimization Strategies for Physics-Informed Neural Networks

2026-06-18 · Fedor Buzaev, Dmitry Efremenko, Egor Bugaev, Andrei Ermakov 외 arxiv

Physics-Informed Neural Networks (PINNs) solve Partial Differential Equations (PDEs) by embedding physical laws into neural network training. However, their performance suffers from unstable convergence, training plateau…

Hyperparameter Optimization

Learning Instance-Specific Parameters of Black-Box Models Using Differentiable Surrogates

2024-07-23 · Arnisha Khondaker, Nilanjan Ray

Tuning parameters of a non-differentiable or black-box compute is challenging. Existing methods rely mostly on random sampling or grid sampling from the parameter space. Further, with all the current methods, it is not p…

DenoisingHyperparameter OptimizationImage DenoisingSSIM