CTP-Net For Cross-Domain Trajectory Prediction
- URL: http://arxiv.org/abs/2110.11645v1
- Date: Fri, 22 Oct 2021 08:18:31 GMT
- Title: CTP-Net For Cross-Domain Trajectory Prediction
- Authors: Pingxuan Huang, Yanyan Fang, Bo Hu, Shenghua Gao, Jing Li
- Abstract summary: Deep learning based trajectory prediction methods rely on large amount of annotated future trajectories.
It is desirable to adapt the model trained with the annotated source domain trajectories to the target domain.
We propose a Cross-domain Trajectory Prediction Network (CTP-Net), in which LSTMs are used to encode the observed trajectories of both domain.
- Score: 32.71173331555378
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep learning based trajectory prediction methods rely on large amount of
annotated future trajectories, but may not generalize well to a new scenario
captured by another camera. Meanwhile, annotating trajectories for training a
network for this new scenario is time-consuming and expensive, therefore it is
desirable to adapt the model trained with the annotated source domain
trajectories to the target domain.
To tackle domain adaptation for trajectory prediction, we propose a
Cross-domain Trajectory Prediction Network (CTP-Net), in which LSTMs are used
to encode the observed trajectories of both domain, and their features are
aligned by a cross-domain feature discriminator. Further, considering the
consistency between the observed trajectories and the predicted trajectories in
the target domain, a target domain offset discriminator is utilized to
adversarially regularize the future trajectory predictions to be consistent
with the observed trajectories. Extensive experiments demonstrate the
effectiveness of the proposed domain adaptation for trajectory prediction
setting as well as our method on domain adaptation for trajectory prediction.
Related papers
- Recurrent Aligned Network for Generalized Pedestrian Trajectory
Prediction [43.98749443981923]
Pedestrian trajectory prediction is a crucial component in computer vision and robotics.
Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model.
We introduce a Recurrent Aligned Network(RAN) to minimize the domain gap through domain alignment.
arXiv Detail & Related papers (2024-03-09T06:17:09Z) - Progressive Conservative Adaptation for Evolving Target Domains [76.9274842289221]
Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain.
Restoring and adapting to such target data results in escalating computational and resource consumption over time.
We propose a simple yet effective approach, termed progressive conservative adaptation (PCAda)
arXiv Detail & Related papers (2024-02-07T04:11:25Z) - Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction [15.454206825258169]
Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles.
Recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians.
This paper proposes a graph transformer structure to improve prediction performance.
arXiv Detail & Related papers (2024-01-10T01:50:29Z) - Label Alignment Regularization for Distribution Shift [63.228879525056904]
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix.
We propose a regularization method for unsupervised domain adaptation that encourages alignment between the predictions in the target domain and its top singular vectors.
We report improved performance over domain adaptation baselines in well-known tasks such as MNIST-USPS domain adaptation and cross-lingual sentiment analysis.
arXiv Detail & Related papers (2022-11-27T22:54:48Z) - Improving Diversity of Multiple Trajectory Prediction based on
Map-adaptive Lane Loss [12.963269946571476]
This study proposes a novel loss function, textitLane Loss, that ensures map-adaptive diversity and accommodates geometric constraints.
Experiments performed on the Argoverse dataset show that the proposed method significantly improves the diversity of the predicted trajectories.
arXiv Detail & Related papers (2022-06-17T09:09:51Z) - Adaptive Trajectory Prediction via Transferable GNN [74.09424229172781]
We propose a novel Transferable Graph Neural Network (T-GNN) framework, which jointly conducts trajectory prediction as well as domain alignment in a unified framework.
Specifically, a domain invariant GNN is proposed to explore the structural motion knowledge where the domain specific knowledge is reduced.
An attention-based adaptive knowledge learning module is further proposed to explore fine-grained individual-level feature representation for knowledge transfer.
arXiv Detail & Related papers (2022-03-09T21:08:47Z) - Ranking Distance Calibration for Cross-Domain Few-Shot Learning [91.22458739205766]
Recent progress in few-shot learning promotes a more realistic cross-domain setting.
Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited.
We employ a re-ranking process for calibrating a target distance matrix by discovering the reciprocal k-nearest neighbours within the task.
arXiv Detail & Related papers (2021-12-01T03:36:58Z) - Human Trajectory Prediction via Counterfactual Analysis [87.67252000158601]
Forecasting human trajectories in complex dynamic environments plays a critical role in autonomous vehicles and intelligent robots.
Most existing methods learn to predict future trajectories by behavior clues from history trajectories and interaction clues from environments.
We propose a counterfactual analysis method for human trajectory prediction to investigate the causality between the predicted trajectories and input clues.
arXiv Detail & Related papers (2021-07-29T17:41:34Z) - Instance Level Affinity-Based Transfer for Unsupervised Domain
Adaptation [74.71931918541748]
We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process.
We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
arXiv Detail & Related papers (2021-04-03T01:33:14Z) - Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position
Estimation [1.20855096102517]
We present Goal-GAN, an interpretable and end-to-end trainable model for human trajectory prediction.
Inspired by human navigation, we model the task of trajectory prediction as an intuitive two-stage process.
arXiv Detail & Related papers (2020-10-02T17:17:45Z)
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.