Segment an object into parts with only one example by using GAN with PFTGAN
Segment an object into parts with only one example by using GAN with PFTGAN
Leveraging GAN Priors for Few-Shot Part Segmentation
arXiv paper abstract https://arxiv.org/abs/2207.13428v1
arXiv PDF paper https://arxiv.org/pdf/2207.13428v1.pdf
Few-shot part segmentation aims to separate different parts of an object given only a few annotated samples.
... existing works mainly focus on learning classifiers over pre-trained features, failing to learn task-specific features for part segmentation.
... propose to learn task-specific features in a "pre-training"-"fine-tuning" paradigm.
... design a fine-tuning strategy to progressively tune an image generator into a segmentation generator, where the supervision of the generator varying from images to segmentation maps by interpolation.
... propose a two-stream architecture, i.e., a segmentation stream to generate task-specific features, and an image stream to provide spatial constraints.
... Extensive experiments show that ... model can achieve state-of-the-art performance on several part segmentation datasets.
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