AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DenseTNT: End-to-End Trajectory Prediction From Dense Goal Sets

Junru Gu, Chen Sun, Hang Zhao

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 559 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
use dense goal probability estimation instead of sparse anchors (with NMS) (ablation)DenseTNT · Argoverse valMiss Rate: 10.1% -> 8.6%Improved
add offline optimization pseudo-labels instead of NMS selection (ablation)DenseTNT · Argoverse valMiss Rate: 8.2% -> 7.0%Improved
add offline optimization pseudo-labels instead of NMS selection (ablation)DenseTNT · Argoverse valminFDE: 1.28 -> 1.27Improved
make the model end-to-end with a goal set predictor (ablation)DenseTNT · Argoverse valMiss Rate: 7.0% -> 7.0%No clear effect
replace variety loss with dense probability and optimization (ablation)TNT-style sparse · Argoverse valMiss Rate: 13.3% -> 7.0%Improved
optimize minFDE objective instead of MR (ablation)DenseTNT · Argoverse valminFDE: 1.27 -> 1.05Improved
optimize minFDE objective instead of MR (ablation)DenseTNT · Argoverse valMiss Rate: 7.0% -> 9.8%Hurt
reduce sampling density from 1.0m to 3.0m (ablation)DenseTNT · Argoverse valMiss Rate: 7.0% -> 12.5%Hurt
refine sampling density from 1.0m to 0.5m (ablation)DenseTNT · Argoverse valMiss Rate: 7.0% -> 7.0%No clear effect
increase optimization time from 20ms to 100ms (ablation)DenseTNT · Argoverse valMiss Rate: 7.6% -> 7.0%Improved
increase optimization time from 100ms to 500ms (ablation)DenseTNT · Argoverse valMiss Rate: 7.0% -> 6.9%No clear effect
mix minFDE and MR objectives 70%/30% instead of pure MR (ablation)DenseTNT · Argoverse valminFDE: 1.27 -> 1.08Improved

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