Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories

TL;DR

This paper introduces a contrastive learning framework using Transformer encoders to generate lightweight, interpretable embeddings for short trajectories, improving retrieval accuracy and efficiency in motion forecasting tasks.

Contribution

It proposes a novel contrastive learning approach with Transformer models for trajectory embedding, emphasizing interpretability and efficiency over heuristic methods.

Findings

Cosine similarity-based embeddings outperform FFT in clustering and retrieval tasks.

Low-dimensional Transformer embeddings (as small as 4D) maintain high performance.

Embeddings enable scalable, transparent motion forecasting.

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.