Image retrieval using an image and a description of what to modify
Image retrieval using an image and a description of what to modify
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
arXiv paper abstract https://arxiv.org/abs/2108.04024
arXiv PDF paper https://arxiv.org/pdf/2108.04024.pdf
Project Web page https://cuberick-orion.github.io/CIRR
We extend the task of composed image retrieval, where an input query consists of an image and short textual description of how to modify the image.
Existing methods have only been applied to non-complex images within narrow domains, such as fashion products, thereby limiting the scope of study
... collect the Compose Image Retrieval on Real-life images (CIRR) dataset, which consists of over 36,000 pairs of crowd-sourced, open-domain images with human-generated modifying text.
... propose CIRPLANT, a transformer based model that leverages rich pre-trained vision-and-language (V&L) knowledge for modifying visual features conditioned on natural language.
Retrieval is then done by nearest neighbor lookup on the modified features.
... CIRPLANT outperforms existing methods on open-domain images, while matching state-of-the-art accuracy on the existing narrow datasets, such as fashion. ...
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
Comments