Segment object even amid similar ones by text-to-image model features without more training with PDM
Segment object even amid similar ones by text-to-image model features without more training with PDM
Unveiling the Power of Diffusion Features For Personalized Segmentation and Retrieval
arXiv paper abstract https://arxiv.org/abs/2405.18025
arXiv PDF paper https://arxiv.org/pdf/2405.18025
Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance.
… supervised methods … require extensive labeled data for training … self-supervised foundation models … showing comparable results to supervised methods.
However, a significant flaw in these models is evident: they struggle to locate a desired instance when other instances within the same class are presented.
In this paper, … explore text-to-image diffusion models for these tasks.
… propose … PDM for Personalized Features Diffusion Matching, that leverages intermediate features of pre-trained text-to-image models for personalization tasks without any additional training.
PDM demonstrates superior performance on popular retrieval and segmentation benchmarks, outperforming even supervised methods …
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
