AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map

Chenfeng Xu, Tian Li, Chen Tang, Lingfeng Sun, Kurt Keutzer, Masayoshi Tomizuka, Alireza Fathi, Wei Zhan

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add PreTraM pre-training (TMCL + MCL)AgentFormer · nuScenes valFDE-10: 3.902 -> 3.687Improved
add PreTraM pre-training (TMCL + MCL)Trajectron++ · nuScenes valFDE-10: 3.221 -> 3.040Improved
add PreTraM pre-trainingTrajectron++ · nuScenesKDE NLL: 2.487 -> 2.380Improved
add PreTraM pre-trainingTrajectron++ · nuScenesBoundary violation rate (%): 23.7 -> 21.9Improved
add trajectory-map contrastive learning (TMCL) to MCL (ablation)PreTraM-AgentFormer · nuScenes val (Map-CNN)ADE-5: 2.442 -> 2.391Improved
add map contrastive learning (MCL) to TMCL (ablation)PreTraM-AgentFormer · nuScenes val (Map-CNN)ADE-5: 2.451 -> 2.391Improved
use TMCL instead of masked trajectory modeling alongside MCL (ablation)PreTraM-AgentFormer · nuScenes val (Map-CNN)FDE-5: 5.322 -> 5.177Improved
load pretrained trajectory encoder in addition to map encoder (ablation)PreTraM-AgentFormer · nuScenes val (Map-CNN)ADE-5: 2.454 -> 2.391Improved
load pretrained map encoder in addition to trajectory encoder (ablation)PreTraM-AgentFormer · nuScenes val (Map-CNN)ADE-5: 2.399 -> 2.391No clear effect
use dropout rather than rotation as MCL augmentation (ablation)PreTraM-AgentFormer · nuScenes val (ResNet18)ADE-5: 2.508 -> 2.372Improved
use dropout rather than gaussian noise as MCL augmentation (ablation)PreTraM-AgentFormer · nuScenes val (ResNet18)FDE-5: 5.601 -> 5.183Improved
train on 10% of trajectory data with PreTraMAgentFormer (ResNet18) · nuScenes val, 10% trajectoriesADE-5: 3.818 -> 3.618Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy