Unsupervised Multi-Object Segmentation Using Attention and Soft-Argmax
Abstract
We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present in the scene and to associate a feature vector to each object. A transformer encoder handles occlusions and redundant detections, and a convolutional autoencoder is in charge of background reconstruction. We show that this architecture significantly outperforms the state of the art on complex synthetic benchmarks.
Cite
Text
Sauvalle and de La Fortelle. "Unsupervised Multi-Object Segmentation Using Attention and Soft-Argmax." Winter Conference on Applications of Computer Vision, 2023.Markdown
[Sauvalle and de La Fortelle. "Unsupervised Multi-Object Segmentation Using Attention and Soft-Argmax." Winter Conference on Applications of Computer Vision, 2023.](https://mlanthology.org/wacv/2023/sauvalle2023wacv-unsupervised/)BibTeX
@inproceedings{sauvalle2023wacv-unsupervised,
title = {{Unsupervised Multi-Object Segmentation Using Attention and Soft-Argmax}},
author = {Sauvalle, Bruno and de La Fortelle, Arnaud},
booktitle = {Winter Conference on Applications of Computer Vision},
year = {2023},
pages = {3267-3276},
url = {https://mlanthology.org/wacv/2023/sauvalle2023wacv-unsupervised/}
}