UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction
- URL: http://arxiv.org/abs/2403.15098v2
- Date: Wed, 27 Mar 2024 10:26:23 GMT
- Title: UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction
- Authors: Lan Feng, Mohammadhossein Bahari, Kaouther Messaoud Ben Amor, Éloi Zablocki, Matthieu Cord, Alexandre Alahi,
- Abstract summary: We introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria.
We conduct extensive experiments and find that model performance significantly drops when transferred to other datasets.
We provide insights into dataset characteristics to explain these findings.
- Score: 93.77809355002591
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, e.g., in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria, presenting new opportunities for the vehicle trajectory prediction field. In particular, using UniTraj, we conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. However, enlarging data size and diversity can substantially improve performance, leading to a new state-of-the-art result for the nuScenes dataset. We provide insights into dataset characteristics to explain these findings. The code can be found here: https://github.com/vita-epfl/UniTraj
Related papers
- Improving Transferability for Cross-domain Trajectory Prediction via
Neural Stochastic Differential Equation [41.09061877498741]
discrepancies exist among datasets due to external factors and data acquisition strategies.
The proficient performance of models trained on large-scale datasets has limited transferability on other small-size datasets.
We propose a method based on continuous and utilization of Neural Differential Equations (NSDE) for alleviating discrepancies.
The effectiveness of our method is validated against state-of-the-art trajectory prediction models on the popular benchmark datasets: nuScenes, Argoverse, Lyft, INTERACTION, and Open Motion dataset.
arXiv Detail & Related papers (2023-12-26T06:50:29Z) - trajdata: A Unified Interface to Multiple Human Trajectory Datasets [32.93180256927027]
We present trajdata, a unified interface to multiple human trajectory datasets.
Trajdata provides a simple, uniform, and efficient representation and API for trajectory and map data.
arXiv Detail & Related papers (2023-07-26T02:45:59Z) - LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting [65.71129509623587]
Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning.
However, the promising results achieved on current public datasets may not be applicable to practical scenarios.
We introduce the LargeST benchmark dataset, which includes a total of 8,600 sensors in California with a 5-year time coverage.
arXiv Detail & Related papers (2023-06-14T05:48:36Z) - infoVerse: A Universal Framework for Dataset Characterization with
Multidimensional Meta-information [68.76707843019886]
infoVerse is a universal framework for dataset characterization.
infoVerse captures multidimensional characteristics of datasets by incorporating various model-driven meta-information.
In three real-world applications (data pruning, active learning, and data annotation), the samples chosen on infoVerse space consistently outperform strong baselines.
arXiv Detail & Related papers (2023-05-30T18:12:48Z) - Combining datasets to increase the number of samples and improve model
fitting [7.4771091238795595]
We propose a novel framework called Combine datasets based on Imputation (ComImp)
In addition, we propose a variant of ComImp that uses Principle Component Analysis (PCA), PCA-ComImp in order to reduce dimension before combining datasets.
Our results indicate that the proposed methods are somewhat similar to transfer learning in that the merge can significantly improve the accuracy of a prediction model on smaller datasets.
arXiv Detail & Related papers (2022-10-11T06:06:37Z) - TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual
Environments [84.6017003787244]
This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets.
We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
arXiv Detail & Related papers (2022-08-16T20:46:08Z) - Detection Hub: Unifying Object Detection Datasets via Query Adaptation
on Language Embedding [137.3719377780593]
A new design (named Detection Hub) is dataset-aware and category-aligned.
It mitigates the dataset inconsistency and provides coherent guidance for the detector to learn across multiple datasets.
The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding.
arXiv Detail & Related papers (2022-06-07T17:59:44Z) - Comparing Test Sets with Item Response Theory [53.755064720563]
We evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples.
We find that Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models.
We also observe span selection task format, which is used for QA datasets like QAMR or SQuAD2.0, is effective in differentiating between strong and weak models.
arXiv Detail & Related papers (2021-06-01T22:33:53Z) - IDDA: a large-scale multi-domain dataset for autonomous driving [16.101248613062292]
This paper contributes a new large scale, synthetic dataset for semantic segmentation with more than 100 different source visual domains.
The dataset has been created to explicitly address the challenges of domain shift between training and test data in various weather and view point conditions.
arXiv Detail & Related papers (2020-04-17T15:22:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.