Reciprocal Learning Networks for Human Trajectory Prediction

• URL: http://arxiv.org/abs/2004.04340v1
• Date: Thu, 9 Apr 2020 02:50:29 GMT
• Title: Reciprocal Learning Networks for Human Trajectory Prediction
• Authors: Hao Sun, Zhiqun Zhao and Zhihai He
• Abstract summary: We develop a new approach, called reciprocal learning, for human trajectory prediction. We borrow the concept of adversarial attacks of deep neural networks, which iteratively modifies the input of the network to match the given or forced network output. Our new method outperforms the state-of-the-art methods for human trajectory prediction.
• Score: 31.390399065230017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We observe that the human trajectory is not only forward predictable, but also backward predictable. Both forward and backward trajectories follow the same social norms and obey the same physical constraints with the only difference in their time directions. Based on this unique property, we develop a new approach, called reciprocal learning, for human trajectory prediction. Two networks, forward and backward prediction networks, are tightly coupled, satisfying the reciprocal constraint, which allows them to be jointly learned. Based on this constraint, we borrow the concept of adversarial attacks of deep neural networks, which iteratively modifies the input of the network to match the given or forced network output, and develop a new method for network prediction, called reciprocal attack for matched prediction. It further improves the prediction accuracy. Our experimental results on benchmark datasets demonstrate that our new method outperforms the state-of-the-art methods for human trajectory prediction.

Related papers

• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback [23.687223152464988]
  We propose DeFeeNet, a simple yet effective network that can be added on existing one-off prediction models. We show that our proposed network improves consecutive human motion prediction performance regardless of the basic model.
  arXiv  Detail & Related papers  (2023-04-10T10:18:23Z)
• Learning from Predictions: Fusing Training and Autoregressive Inference for Long-Term Spatiotemporal Forecasts [4.068387278512612]
  We propose the Scheduled Autoregressive BPTT (BPTT-SA) algorithm for predicting complex systems. Our results show that BPTT-SA effectively reduces iterative error propagation in Convolutional RNNs and Convolutional Autoencoder RNNs.
  arXiv  Detail & Related papers  (2023-02-22T02:46:54Z)
• Parallel Reasoning Network for Human-Object Interaction Detection [53.422076419484945]
  We propose a new transformer-based method named Parallel Reasoning Network(PR-Net) PR-Net constructs two independent predictors for instance-level localization and relation-level understanding. Our PR-Net has achieved competitive results on HICO-DET and V-COCO benchmarks.
  arXiv  Detail & Related papers  (2023-01-09T17:00:34Z)
• Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network [65.11999700562869]
  We propose a novel collaborative prediction unit (CoPU), which aggregates predictions from multiple collaborative predictors according to a collaborative graph. Our methods outperform state-of-the-art works on the three tasks by 28.6%, 17.4% and 21.0% on average.
  arXiv  Detail & Related papers  (2021-07-02T08:20:06Z)
• Predicting Deep Neural Network Generalization with Perturbation Response Curves [58.8755389068888]
  We propose a new framework for evaluating the generalization capabilities of trained networks. Specifically, we introduce two new measures for accurately predicting generalization gaps. We attain better predictive scores than the current state-of-the-art measures on a majority of tasks in the Predicting Generalization in Deep Learning (PGDL) NeurIPS 2020 competition.
  arXiv  Detail & Related papers  (2021-06-09T01:37:36Z)
• Interpretable Social Anchors for Human Trajectory Forecasting in Crowds [84.20437268671733]
  We propose a neural network-based system to predict human trajectory in crowds. We learn interpretable rule-based intents, and then utilise the expressibility of neural networks to model scene-specific residual. Our architecture is tested on the interaction-centric benchmark TrajNet++.
  arXiv  Detail & Related papers  (2021-05-07T09:22:34Z)
• Adversarial Refinement Network for Human Motion Prediction [61.50462663314644]
  Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend. We propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation.
  arXiv  Detail & Related papers  (2020-11-23T05:42:20Z)
• Depth Uncertainty in Neural Networks [2.6763498831034043]
  Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes. By exploiting the sequential structure of feed-forward networks, we are able to both evaluate our training objective and make predictions with a single forward pass. We validate our approach on real-world regression and image classification tasks.
  arXiv  Detail & Related papers  (2020-06-15T14:33:40Z)

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.