AI Paper Atlas

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

Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction

Mozhgan Pourkeshavarz, Changhe Chen, Amir Rasouli

ICCV 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervision in supervised pipelines · 20 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 TAROT-prediction self-supervised HSL tasks balanced by MENTOR (ablation)HGT trajectory predictor · Argoverse turnsDAO: 68.45 -> 79.21Improved
add a single TAROT proxy task (length 6) (ablation)HGT trajectory predictor · Argoverse turnsDAO: 68.45 -> 76.93Improved
increase TAROT length from 6 to 8 (ablation)single-TAROT HSL task · Argoverse turnsDAO: 76.93 -> 73.65Hurt
combine multiple TAROT lengths via MENTOR instead of a single best TAROT (ablation)HSL tasks · Argoverse turnsDAO: 76.93 -> 79.21Improved
run four SSL tasks through MENTOR instead of adding them individually (ablation)lane-graph baseline · Argoverse validationDAO: 69.97 -> 77.91Improved
add SSL task B (distance to intersection) alone (ablation)lane-graph baseline · Argoverse validationRF: 3.00 -> 3.87Improved
add SSL task A (lane masking) alone (ablation)lane-graph baseline · Argoverse validationRF: 3.00 -> 2.98No clear effect
use MENTOR instead of HiVT on challenging turn scenariostrajectory prediction · Argoverse turnsDAO: 66.84 -> 79.21Improved
use MENTOR instead of HiVT on the full Argoverse test settrajectory prediction · Argoverse testminFDE: 1.16 -> 1.21Hurt
remove loss-based weighting of proxy tasks (naive multi-task combination) (ablation)multi-task HSL training · Argoverseprimary task performanceHurt

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