Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance.In this regard, we focus on delivering accurate predictions when only few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting / Monti, A.; Porrello, A.; Calderara, S.; Coscia, P.; Ballan, L.; Cucchiara, R.. - 2022-June:(2022), pp. 6543-6552. (Intervento presentato al convegno 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 tenutosi a New Orleans USA nel 19/06/2022) [10.1109/CVPR52688.2022.00644].

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

Monti A.;Porrello A.;Calderara S.;Cucchiara R.
2022

Abstract

Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance.In this regard, we focus on delivering accurate predictions when only few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.
2022
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
New Orleans USA
19/06/2022
2022-June
6543
6552
Monti, A.; Porrello, A.; Calderara, S.; Coscia, P.; Ballan, L.; Cucchiara, R.
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting / Monti, A.; Porrello, A.; Calderara, S.; Coscia, P.; Ballan, L.; Cucchiara, R.. - 2022-June:(2022), pp. 6543-6552. (Intervento presentato al convegno 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 tenutosi a New Orleans USA nel 19/06/2022) [10.1109/CVPR52688.2022.00644].
File in questo prodotto:
File Dimensione Formato  
Monti_How_Many_Observations_Are_Enough_Knowledge_Distillation_for_Trajectory_Forecasting_CVPR_2022_paper.pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 1.46 MB
Formato Adobe PDF
1.46 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1317187
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 6
social impact