AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks

arXiv:2402.15351v1 Announce Type: new
Abstract: Automated machine learning (AutoML) is a collection of techniques designed to automate the machine learning development process. While traditional AutoML approaches have been successfully applied in several critical steps of model development (e.g. hyperparameter optimization), there lacks a AutoML system that automates the entire end-to-end model production workflow. To fill this blank, we present AutoMMLab, a general-purpose LLM-empowered AutoML system that follows user's language instructions to automate the whole model production workflow for computer vision …

abstract arxiv automate automated automated machine learning automl collection computer computer vision cs.cv cs.lg development hyperparameter language machine machine learning model development optimization process tasks type vision