AI Paper Atlas

Research map / Image generation / GANs

MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

Patrick Dendorfer, Sven Elflein, Laura Leal-Taixé

ICCV 2021 · Image generation › GANs · approach: Generative adversarial network theory · 145 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 multiple generators (4 instead of 1) without classifier or PM-Net (ablation)single-generator GAN · Synthetic datasetPrecision / Recall: precision 0.46 -> 0.37; recall 0.48 -> 0.68Mixed
add PM-Net on top of multiple generators (ablation)multi-generator GAN · Synthetic datasetPrecision: 0.37 -> 0.72Improved
add classifier C on top of multiple generators (ablation)multi-generator GAN · Synthetic datasetPrecision: 0.37 -> 0.73Improved
add PM-Net and classifier together (ablation)multi-generator GAN · Synthetic datasetPrecision: 0.72 -> 0.77Improved
use 4 generators instead of one generator at the same total parameter count (ablation)GAN+L2 · Synthetic datasetADE/FDE and recall/precision: 50% (ADE/FDE), 30% (recall/precision)Improved
use expectation sampling with PM-Net instead of random sampling over generators (ablation)MG-GAN · Synthetic datasetRecallImproved
vary number of generators n_G from 2 to 8 (ablation)MG-GAN · ETH/UCYADE / FDE: ADE 0.36-0.39, FDE 0.70-0.76No clear effect
raise lambda_Traj from 0.1 to 5.0 (lambda_Cl = 1.0) (ablation)MG-GAN (n_G=5) · Synthetic datasetPrecision: 0.64 -> 0.81Improved
raise lambda_Cl from 0.1 to 5.0 (lambda_Traj = 1.0) (ablation)MG-GAN (n_G=5) · Synthetic datasetPrecision: 0.73 -> 0.76No clear effect
vary sigma of PM-Net training from 0.1 to 5.0 (ablation)MG-GAN (n_G=5) · Synthetic datasetPrecision: 0.77 (0.1), 0.70 (0.5), 0.80 (2.5), 0.72 (5.0)No clear effect
raise generator training samples q from 1 to 20 (l=5) (ablation)MG-GAN (n_G=5) · Synthetic datasetPrecision: 0.33 -> 0.79Improved
raise PM-Net samples l from 1 to 5 (q=20) (ablation)MG-GAN (n_G=5) · Synthetic datasetPrecision: 0.57 -> 0.79Improved

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