Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation

Abstract
Best-of-N (BoN) Average Displacement Error (ADE)/ Final Displacement Error (FDE) is the most used metric for evaluating trajectory prediction models. Yet, the BoN does not quantify the whole generated samples, resulting in an incomplete view of the model’s prediction quality and performance. We propose a new metric, Average Mahalanobis Distance (AMD) to tackle this issue. AMD is a metric that quantifies how close the whole generated samples are to the ground truth. We also introduce the Average Maximum Eigenvalue (AMV) metric that quantifies the overall spread of the predictions. Our metrics are validated empirically by showing that the ADE/FDE is not sensitive to distribution shifts, giving a biased sense of accuracy, unlike the AMD/AMV metrics. We introduce the usage of Implicit Maximum Likelihood Estimation (IMLE) as a replacement for traditional generative models to train our model, Social-Implicit. IMLE training mechanism aligns with AMD/AMV objective of predicting trajectories that are close to the ground truth with a tight spread. Social-Implicit is a memory efficient deep model with only 5.8K parameters that runs in real time of 580 Hz and achieves competitive results.

Citation
Mohamed, A., Zhu, D., Vu, W., Elhoseiny, M., & Claudel, C. (2022). Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation. Computer Vision – ECCV 2022, 463–479. https://doi.org/10.1007/978-3-031-20047-2_27

Publisher
Springer Nature Switzerland

Conference/Event Name
17th European Conference on Computer Vision, ECCV 2022

DOI
10.1007/978-3-031-20047-2_27

arXiv
2203.03057

Additional Links
https://link.springer.com/10.1007/978-3-031-20047-2_27

Relations
Is Supplemented By:
  • [Software]
    Title: abduallahmohamed/Social-Implicit: Code for: "Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation" Accepted @ ECCV2022. Publication Date: 2021-11-22. github: abduallahmohamed/Social-Implicit Handle: 10754/686453

Permanent link to this record

Version History

Now showing 1 - 2 of 2
VersionDateSummary
2*
2022-12-05 12:06:37
Published as conference paper
2022-05-16 08:59:30
* Selected version