How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

• URL: http://arxiv.org/abs/2203.04781v1
• Date: Wed, 9 Mar 2022 15:05:39 GMT
• Title: How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
• Authors: Alessio Monti, Angelo Porrello, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara
• Abstract summary: Current state-of-the-art models usually rely on a "history" of past tracked locations to predict a plausible sequence of future locations. We conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one. We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches.
• Score: 31.57539055861249
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning 3D Perception from Others' Predictions [64.09115694891679]
  We investigate a new scenario to construct 3D object detectors: learning from the predictions of a nearby unit that is equipped with an accurate detector. For example, when a self-driving car enters a new area, it may learn from other traffic participants whose detectors have been optimized for that area.
  arXiv  Detail & Related papers  (2024-10-03T16:31:28Z)
• EANet: Expert Attention Network for Online Trajectory Prediction [5.600280639034753]
  Expert Attention Network is a complete online learning framework for trajectory prediction. We introduce expert attention, which adjusts the weights of different depths of network layers, avoiding the model updated slowly due to gradient problem. Furthermore, we propose a short-term motion trend kernel function which is sensitive to scenario change, allowing the model to respond quickly.
  arXiv  Detail & Related papers  (2023-09-11T07:09:40Z)
• Prior Knowledge Guided Network for Video Anomaly Detection [1.389970629097429]
  Video Anomaly Detection (VAD) involves detecting anomalous events in videos. We propose a Prior Knowledge Guided Network(PKG-Net) for the VAD task.
  arXiv  Detail & Related papers  (2023-09-04T15:57:07Z)
• Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving [68.95178518732965]
  A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants. Existing works either perform object detection followed by trajectory of the detected objects, or predict dense occupancy and flow grids for the whole scene. This motivates our unified approach to perception and future prediction that implicitly represents occupancy and flow over time with a single neural network.
  arXiv  Detail & Related papers  (2023-08-02T23:39:24Z)
• Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences [12.650574326251023]
  In this paper, we explore the extension of a self-supervised loss for scene flow prediction. Regarding the KITTI scene flow benchmark, our method outperforms the corresponding supervised pre-training of the same network.
  arXiv  Detail & Related papers  (2022-06-30T13:55:17Z)
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors [82.91398970736391]
  Vehicle trajectory prediction tasks have been commonly tackled from two perspectives: knowledge-driven or data-driven. In this paper, we propose to learn a "Realistic Residual Block" (RRB) which effectively connects these two perspectives. Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty.
  arXiv  Detail & Related papers  (2021-03-08T16:03:09Z)
• Attentional-GCNN: Adaptive Pedestrian Trajectory Prediction towards Generic Autonomous Vehicle Use Cases [10.41902340952981]
  We propose a novel Graph Convolutional Neural Network (GCNN)-based approach, Attentional-GCNN, which aggregates information of implicit interaction between pedestrians in a crowd by assigning attention weight in edges of the graph. We show our proposed method achieves an improvement over the state of art by 10% Average Displacement Error (ADE) and 12% Final Displacement Error (FDE) with fast inference speeds.
  arXiv  Detail & Related papers  (2020-11-23T03:13:26Z)
• Predicting MOOCs Dropout Using Only Two Easily Obtainable Features from the First Week's Activities [56.1344233010643]
  Several features are considered to contribute towards learner attrition or lack of interest, which may lead to disengagement or total dropout. This study aims to predict dropout early-on, from the first week, by comparing several machine-learning approaches.
  arXiv  Detail & Related papers  (2020-08-12T10:44:49Z)
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction [57.56466850377598]
  Reasoning over visual data is a desirable capability for robotics and vision-based applications. In this paper, we present a framework on graph to uncover relationships in different objects in the scene for reasoning about pedestrian intent. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is a very crucial piece of information for autonomous vehicles.
  arXiv  Detail & Related papers  (2020-02-20T18:50:44Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.