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.
@article{arxiv.2205.13271,
title = {Unsupervised Multi-object Segmentation Using Attention and Soft-argmax},
author = {Bruno Sauvalle and Arnaud de La Fortelle},
journal= {arXiv preprint arXiv:2205.13271},
year = {2022}
}