Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <title>Title</title> | |
| </head> | |
| <body> | |
| Try this demo for <a href="https://github.com/hasibzunair/peekaboo">PEEKABOO</a>, | |
| introduced in our <strong>BMVC'2024</strong> paper <a href="https://arxiv.org/abs/2407.17628">PEEKABOO: Hiding Parts of an Image for Unsupervised Object Localization</a>. | |
| </br> | |
| Peekaboo aims to explicitly model contextual relationship among pixels through image masking for unsupervised object localization. | |
| In a self-supervised procedure (i.e. pretext task) without any additional training (i.e. downstream task), context-based representation learning is done at both | |
| the pixel-level by making predictions on masked images and at shape-level by matching the predictions of the masked input to the unmasked one. | |
| </br> | |
| You can use this demo to segment the most salient object(s) in your images. To use it, simply | |
| upload an image of your choice and hit submit. You will get one or more segmentation maps of the most salient objects present | |
| in your images. | |
| </br> | |
| <a href="https://hasibzunair.github.io/peekaboo/"><strong>Project Page</strong></a> | |
| </br> | |
| </body> | |
| </html> |