AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916226113994752 |
|---|---|
| author | Mercurius, Ray Coden Ahmadi, Ehsan Shabestary, Soheil Mohamad Alizadeh Rasouli, Amir |
| author_facet | Mercurius, Ray Coden Ahmadi, Ehsan Shabestary, Soheil Mohamad Alizadeh Rasouli, Amir |
| contents | Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of samples. However, the existing naturalistic trajectory prediction datasets are generally imbalanced in favor of simpler samples and lack challenging scenarios. Such a long-tail effect causes prediction models to underperform on the tail portion of the data distribution containing safety-critical scenarios. Previous methods tackle the long-tail problem using methods such as contrastive learning and class-conditioned hypernetworks. These approaches, however, are not modular and cannot be applied to many machine learning architectures. In this work, we propose a modular model-agnostic framework for trajectory prediction that leverages a specialized mixture of experts. In our approach, each expert is trained with a specialized skill with respect to a particular part of the data. To produce predictions, we utilise a router network that selects the best expert by generating relative confidence scores. We conduct experimentation on common pedestrian trajectory prediction datasets and show that our method improves performance on long-tail scenarios. We further conduct ablation studies to highlight the contribution of different proposed components. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08698 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction Mercurius, Ray Coden Ahmadi, Ehsan Shabestary, Soheil Mohamad Alizadeh Rasouli, Amir Computer Vision and Pattern Recognition Machine Learning Robotics Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of samples. However, the existing naturalistic trajectory prediction datasets are generally imbalanced in favor of simpler samples and lack challenging scenarios. Such a long-tail effect causes prediction models to underperform on the tail portion of the data distribution containing safety-critical scenarios. Previous methods tackle the long-tail problem using methods such as contrastive learning and class-conditioned hypernetworks. These approaches, however, are not modular and cannot be applied to many machine learning architectures. In this work, we propose a modular model-agnostic framework for trajectory prediction that leverages a specialized mixture of experts. In our approach, each expert is trained with a specialized skill with respect to a particular part of the data. To produce predictions, we utilise a router network that selects the best expert by generating relative confidence scores. We conduct experimentation on common pedestrian trajectory prediction datasets and show that our method improves performance on long-tail scenarios. We further conduct ablation studies to highlight the contribution of different proposed components. |
| title | AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction |
| topic | Computer Vision and Pattern Recognition Machine Learning Robotics |
| url | https://arxiv.org/abs/2402.08698 |