Contrast&Compress: Learning Lightweight Embeddings for Short Trajectories

2025-06-03

AI Summary

Retrieving short trajectories with dual similarity in semantics and direction remains challenging due to the insensitivity of conventional metrics (e.g., FFT) to directional characteristics. Method: This paper proposes a lightweight contrastive learning embedding framework leveraging a Transformer encoder jointly optimized with triplet loss, and introduces— for the first time—a Cosine-based contrastive objective incorporating directional intent modeling. The learned embeddings achieve high discriminability and interpretability while supporting real-time inference, with dimensionality as low as 4D. Results: Evaluated on Argoverse 2, the method significantly improves minADE and minFDE. Even at 4D, it maintains superior retrieval performance while drastically reducing computational overhead, enabling real-time motion prediction and deployment in autonomous navigation systems.

Technology Category

• Computer Vision: Motion & Tracking
• Search and Optimization: Learning to Search
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The ability to retrieve semantically and directionally similar short-range trajectories with both accuracy and efficiency is foundational for downstream applications such as motion forecasting and autonomous navigation. However, prevailing approaches often depend on computationally intensive heuristics or latent anchor representations that lack interpretability and controllability. In this work, we propose a novel framework for learning fixed-dimensional embeddings for short trajectories by leveraging a Transformer encoder trained with a contrastive triplet loss that emphasize the importance of discriminative feature spaces for trajectory data. We analyze the influence of Cosine and FFT-based similarity metrics within the contrastive learning paradigm, with a focus on capturing the nuanced directional intent that characterizes short-term maneuvers. Our empirical evaluation on the Argoverse 2 dataset demonstrates that embeddings shaped by Cosine similarity objectives yield superior clustering of trajectories by both semantic and directional attributes, outperforming FFT-based baselines in retrieval tasks. Notably, we show that compact Transformer architectures, even with low-dimensional embeddings (e.g., 16 dimensions, but qualitatively down to 4), achieve a compelling balance between retrieval performance (minADE, minFDE) and computational overhead, aligning with the growing demand for scalable and interpretable motion priors in real-time systems. The resulting embeddings provide a compact, semantically meaningful, and efficient representation of trajectory data, offering a robust alternative to heuristic similarity measures and paving the way for more transparent and controllable motion forecasting pipelines.

Problem

• Learning lightweight embeddings for short trajectories efficiently
• Improving interpretability and controllability in trajectory similarity metrics
• Balancing retrieval performance and computational overhead in real-time systems

Innovation

• Transformer encoder with contrastive triplet loss
• Cosine similarity for discriminative embeddings
• Compact low-dimensional trajectory representations