
A training dynamics-aware contrastive learning framework that leverages rich contextual information and clustering based on model learning behaviors to improve accuracy and scene compliance on long-tail trajectory prediction samples.


coremsg

a-training-dynamics-aware-contrastive-learning-framework-for-improving-long-tail-trajectory-prediction-in-autonomous-driving


A Training Dynamics-Aware Contrastive Learning Framework for Improving Long-Tail Trajectory Prediction in Autonomous Driving
