Convolutions for Spatial Interaction Modeling
arXiv:2104.07182
Abstract
In many different fields interactions between objects play a critical role in determining their behavior. Graph neural networks (GNNs) have emerged as a powerful tool for modeling interactions, although often at the cost of adding considerable complexity and latency. In this paper, we consider the problem of spatial interaction modeling in the context of predicting the motion of actors around autonomous vehicles, and investigate alternatives to GNNs. We revisit 2D convolutions and show that they can demonstrate comparable performance to graph networks in modeling spatial interactions with lower latency, thus providing an effective and efficient alternative in time-critical systems. Moreover, we propose a novel interaction loss to further improve the interaction modeling of the considered methods.
arXiv commentSupplementary material included, to appear at CVPR2022
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Learning Combinatorial Optimization Algorithms over Graphs
- Feature Pyramid Networks for Object Detection
- Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
- Graph networks as learnable physics engines for inference and control
- IntentNet: Learning to Predict Intention from Raw Sensor Data
- Learning representations of irregular particle-detector geometry with distance-weighted graph networks
- On the Bottleneck of Graph Neural Networks and its Practical Implications
- Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
- Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
- Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
- VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
- Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
- CAR-Net: Clairvoyant Attentive Recurrent Network