AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Likelihood-Based Diverse Sampling for Trajectory Forecasting

Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman, Osbert Bastani

ICCV 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 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 the diversity loss (ablation)LDS-AF · nuScenesminADE_5: 5.95 -> 2.06Improved
add the diversity loss (ablation)LDS-AF · nuScenesminASD_5: 0.16 -> 3.09Improved
add the likelihood loss (ablation)LDS-AF · nuScenesminADE_5: 8.06 -> 2.06Improved
use NLL likelihood loss instead of DLow reconstruction+KL (ablation)LDS-AF · nuScenesminADE_5: 2.16 -> 2.06Improved
use min instead of mean in the diversity loss (ablation)LDS-AF · nuScenesminADE_5: 4.85 -> 2.06Improved
use min instead of mean in the diversity loss (ablation)LDS-AF · nuScenesminASD_10: 0.03 -> 1.98Improved
add epsilon stochasticity to LDS training (ablation)LDS-AF (K=10) · nuScenesminADE_10: 1.74 -> 1.65Improved
apply LDS post-hoc to the CVAECVAE · nuScenesminADE_5: 2.71 -> 2.16Improved
apply LDS post-hoc to the flow modelAF · nuScenesminADE_5: 2.86 -> 2.06Improved
apply DSF post-hoc to CAM-NFCAM-NF · Forking Paths (test, avg of 45-Degree and Top Down)minADE_20: 148.0 -> 162.8Hurt
apply LDS post-hoc to CAM-NFCAM-NF · Forking Paths (test, avg of 45-Degree and Top Down)minADE_20: 148.0 -> 98.6Improved
use transductive neural LDS instead of particle variantLDS-AF · nuScenesminADE_5: 2.46 -> 2.06Improved

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