top of page

News to help your R&D in artificial intelligence, machine learning, robotics, computer vision, smart hardware

As an Amazon Associate I earn

from qualifying purchases

Writer's picturemorrislee

Detect object by train on text-to-image for foreground and background with Text2Image-for-Detection

Detect object by train on text-to-image for foreground and background with Text2Image-for-Detection


Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation

arXiv paper abstract https://arxiv.org/abs/2309.05956



... propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).


The proposed approach decouples training data generation into foreground object generation, and contextually coherent background generation.


To generate foreground objects, ... employ ... object class name as input prompts ... into a text-to-image ... producing various foreground images ... against ... backgrounds. A foreground-background segmentation ... generate foreground object masks.


To generate context images, ... begin by creating language descriptions of the context ... by ... image captioning ... images representing ... context ... descriptions are then transformed into a diverse array of context images via a text-to-image synthesis framework.


... composite these with the foreground object masks produced in the initial step, utilizing a cut-and-paste method, to formulate the training data.


... detectors trained solely on synthetic data produced by ... method achieve performance comparable to those trained on real data ...



Please like and share this post if you enjoyed it using the buttons at the bottom!


Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact

Web site with my other posts by category https://morrislee1234.wixsite.com/website



55 views0 comments

Comments


ClickBank paid link

bottom of page