On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors

Makansi, Osama; Çiçek, Özgün; Marrakchi, Yassine; Brox, Thomas

doi:10.1109/iccv48922.2021.01290

Cited by 24 publications

(18 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[42] proposed a distribution smoothing over label (LDS) and feature space (FDS) for imbalanced regression. A concurrent work is [9] where they noticed the long-tail error distribution for trajectory prediction. They used Kalman filter [43] performance as a difficulty measure and utilized contrastive learning to alleviate the tail problem.…”

Section: Related Workmentioning

confidence: 99%

“…There are two main classes of methods for modifying loss functions to improve tail performance: regularization [9,30] and re-weighting [28,29,42]. Both classes are characterized by different behavior on tail data [30].…”

Section: Pareto Lossmentioning

confidence: 99%

“…• Contrastive Loss: [9] uses contrastive loss as a regularizer to group examples together based on Kalman filter prediction errors. • Focal Loss: [28] uses L1 loss to reweigh loss terms.…”

Section: Setupmentioning

confidence: 99%

“…The difference between AR and DeepAR error distributions also suggests that assuming tail overlap between deep learning and non-deep learning methods (such as Kalman filter used by [9]) might not generalize well.…”

Section: Synthetic Dataset Experimentsmentioning

confidence: 99%

“…However, long-tail learning methods in classification are not directly translatable to forecasting as we do not have a pre-defined class. A recent work by [9] propose to use Kalman filter to gauge the difficulty of different forecasting examples but such difficulties may not directly relate to deep neural networks used for the actual forecasting task.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Taming the Long Tail of Deep Probabilistic Forecasting

Kozerawski¹,

Sharan²,

Yu³

2022

Preprint

View full text Add to dashboard Cite

Deep probabilistic forecasting is gaining attention in numerous applications ranging from weather prognosis, through electricity consumption estimation, to autonomous vehicle trajectory prediction. However, existing approaches focus on improvements on the most common scenarios without addressing the performance on rare and difficult cases. In this work, we identify a long tail behavior in the performance of state-of-the-art deep learning methods on probabilistic forecasting. We present two moment-based tailedness measurement concepts to improve performance on the difficult tail examples: Pareto Loss and Kurtosis Loss. Kurtosis loss is a symmetric measurement as the fourth moment about the mean of the loss distribution. Pareto loss is asymmetric measuring right tailedness, modeling the loss using a generalized Pareto distribution (GPD). We demonstrate the performance of our approach on several real-world datasets including time series and spatiotemporal trajectories, achieving significant improvements on the tail examples.

show abstract

Section: Related Workmentioning

confidence: 99%