Sparse Prototype Network for Explainable Pedestrian Behavior Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Yan, Carballo, Alexander, Takeda, Kazuya
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912073869426688
author Feng, Yan
Carballo, Alexander
Takeda, Kazuya
author_facet Feng, Yan
Carballo, Alexander
Takeda, Kazuya
contents Predicting pedestrian behavior is challenging yet crucial for applications such as autonomous driving and smart city. Recent deep learning models have achieved remarkable performance in making accurate predictions, but they fail to provide explanations of their inner workings. One reason for this problem is the multi-modal inputs. To bridge this gap, we present Sparse Prototype Network (SPN), an explainable method designed to simultaneously predict a pedestrian's future action, trajectory, and pose. SPN leverages an intermediate prototype bottleneck layer to provide sample-based explanations for its predictions. The prototypes are modality-independent, meaning that they can correspond to any modality from the input. Therefore, SPN can extend to arbitrary combinations of modalities. Regularized by mono-semanticity and clustering constraints, the prototypes learn consistent and human-understandable features and achieve state-of-the-art performance on action, trajectory and pose prediction on TITAN and PIE. Finally, we propose a metric named Top-K Mono-semanticity Scale to quantitatively evaluate the explainability. Qualitative results show the positive correlation between sparsity and explainability. Code available at https://github.com/Equinoxxxxx/SPN.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12195
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sparse Prototype Network for Explainable Pedestrian Behavior Prediction
Feng, Yan
Carballo, Alexander
Takeda, Kazuya
Computer Vision and Pattern Recognition
Artificial Intelligence
Predicting pedestrian behavior is challenging yet crucial for applications such as autonomous driving and smart city. Recent deep learning models have achieved remarkable performance in making accurate predictions, but they fail to provide explanations of their inner workings. One reason for this problem is the multi-modal inputs. To bridge this gap, we present Sparse Prototype Network (SPN), an explainable method designed to simultaneously predict a pedestrian's future action, trajectory, and pose. SPN leverages an intermediate prototype bottleneck layer to provide sample-based explanations for its predictions. The prototypes are modality-independent, meaning that they can correspond to any modality from the input. Therefore, SPN can extend to arbitrary combinations of modalities. Regularized by mono-semanticity and clustering constraints, the prototypes learn consistent and human-understandable features and achieve state-of-the-art performance on action, trajectory and pose prediction on TITAN and PIE. Finally, we propose a metric named Top-K Mono-semanticity Scale to quantitatively evaluate the explainability. Qualitative results show the positive correlation between sparsity and explainability. Code available at https://github.com/Equinoxxxxx/SPN.
title Sparse Prototype Network for Explainable Pedestrian Behavior Prediction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.12195