SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

Liang, Junwei; Jiang, Lu; Hauptmann, Alexander G.

doi:10.1007/978-3-030-58601-0_17

Cited by 63 publications

(39 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We compare SpecTGNN with several state-of-the-art baselines on both datasets, including CF-VAE [19], P2TIRL [36], SimAug [37], PECNet [38], CSP [39], CAR-Net [40], SpAGNN [41], STGAT [42], Social-STGCNN (S-STGCNN) [14].…”

Section: B Baseline and Evaluation Metricsmentioning

confidence: 99%

Spectral Temporal Graph Neural Network for Trajectory Prediction

Cao¹,

Li²,

Ma³

et al. 2021

Preprint

View full text Add to dashboard Cite

An effective understanding of the contextual environment and accurate motion forecasting of surrounding agents is crucial for the development of autonomous vehicles and social mobile robots. This task is challenging since the behavior of an autonomous agent is not only affected by its own intention, but also by the static environment and surrounding dynamically interacting agents. Previous works focused on utilizing the spatial and temporal information in time domain while not sufficiently taking advantage of the cues in frequency domain. To this end, we propose a Spectral Temporal Graph Neural Network (SpecTGNN), which can capture inter-agent correlations and temporal dependency simultaneously in frequency domain in addition to time domain. SpecTGNN operates on both an agent graph with dynamic state information and an environment graph with the features extracted from context images in two streams. The model integrates graph Fourier transform, spectral graph convolution and temporal gated convolution to encode history information and forecast future trajectories. Moreover, we incorporate a multi-head spatio-temporal attention mechanism to mitigate the effect of error propagation in a long time horizon. We demonstrate the performance of SpecTGNN on two public trajectory prediction benchmark datasets, which achieves stateof-the-art performance in terms of prediction accuracy.

show abstract

Section: B Baseline and Evaluation Metricsmentioning

confidence: 99%

Spectral Temporal Graph Neural Network for Trajectory Prediction

Cao¹,

Li²,

Ma³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Another effective strategy is to directly identify the clean samples and only select them to train the models [9,58,36,38,24,52]. Other contributions in this direction include data augmentation [61,27,5], semi-supervised learning [15,48,24,62], etc.…”

Section: Related Workmentioning

confidence: 99%

Faster Meta Update Strategy for Noise-Robust Deep Learning

Xu¹,

Zhu²,

Jiang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow training is currently the bottleneck in the meta learning approaches. In this paper, we introduce a novel Faster Meta Update Strategy (FaMUS) to replace the most expensive step in the meta gradient computation with a faster layer-wise approximation. We empirically find that FaMUS yields not only a reasonably accurate but also a low-variance approximation of the meta gradient. We conduct extensive experiments to verify the proposed method on two tasks. We show our method is able to save two-thirds of the training time while still maintaining the comparable or achieving even better generalization performance. In particular, our method achieves the stateof-the-art performance on both synthetic and realistic noisy labels, and obtains promising performance on long-tailed recognition on standard benchmarks. Code are released at https://github.com/youjiangxu/FaMUS.

show abstract

“…PLOP [6] and Argoverse [7] use the ego trajectory in a bird's eye view map. Simaug and SMARTS [25,52] take advantage of simulation data to train the prediction model. Others [5,8,11,24,26,49] have explored multimodal inputs, such as Lidar [9,31,36,47], to aid in trajectory prediction.…”

Section: Related Workmentioning

confidence: 99%

Stepwise Goal-Driven Networks for Trajectory Prediction

Wang,

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose to predict the future trajectories of observed agents (e.g., pedestrians or vehicles) by estimating and using their goals at multiple time scales. We argue that the goal of a moving agent may change over time, and modeling goals continuously provides more accurate and detailed information for future trajectory estimation. In this paper, we present a novel recurrent network for trajectory prediction, called Stepwise Goal-Driven Network (SGNet). Unlike prior work that models only a single, long-term goal, SGNet estimates and uses goals at multiple temporal scales. In particular, the framework incorporates an encoder module that captures historical information, a stepwise goal estimator that predicts successive goals into the future, and a decoder module that predicts future trajectory. We evaluate our model on three first-person traffic datasets (HEV-I, JAAD, and PIE) as well as on two bird's eye view datasets (ETH and UCY), and show that our model outperforms the state-of-the-art methods in terms of both average and final displacement errors on all datasets. Code has been made available at: https://github.com/ ChuhuaW/SGNet.pytorch.

show abstract

SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

Cited by 63 publications

References 56 publications

Spectral Temporal Graph Neural Network for Trajectory Prediction

Spectral Temporal Graph Neural Network for Trajectory Prediction

Faster Meta Update Strategy for Noise-Robust Deep Learning

Stepwise Goal-Driven Networks for Trajectory Prediction

Contact Info

Product

Resources

About