Explainable Sparse Attention for Memory-Based Trajectory Predictors
Abstract
In this paper we address the problem of trajectory prediction, focusing on memory-based models. Such methods are trained to collect a set of useful samples that can be retrieved and used at test time to condition predictions. We propose Explainable Sparse Attention (ESA), a module that can be seamlessly plugged-in into several existing memory-based state of the art predictors. ESA generates a sparse attention in memory, thus selecting a small subset of memory entries that are relevant for the observed trajectory. This enables an explanation of the model’s predictions with reference to previously observed training samples. Furthermore, we demonstrate significant improvements on three trajectory prediction datasets.
Cite
Text
Marchetti et al. "Explainable Sparse Attention for Memory-Based Trajectory Predictors." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25072-9_37Markdown
[Marchetti et al. "Explainable Sparse Attention for Memory-Based Trajectory Predictors." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/marchetti2022eccvw-explainable/) doi:10.1007/978-3-031-25072-9_37BibTeX
@inproceedings{marchetti2022eccvw-explainable,
title = {{Explainable Sparse Attention for Memory-Based Trajectory Predictors}},
author = {Marchetti, Francesco and Becattini, Federico and Seidenari, Lorenzo and Del Bimbo, Alberto},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {543-560},
doi = {10.1007/978-3-031-25072-9_37},
url = {https://mlanthology.org/eccvw/2022/marchetti2022eccvw-explainable/}
}