AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

AutoSimulate: (Quickly) Learning Synthetic Data Generation

Harkirat Singh Behl, Atilim Güneş Baydin, Ran Gal, Philip H.S. Torr, Vibhav Vineet

ECCV 2020 · Probabilistic and scientific modeling › Bayesian optimization · approach: Multi-fidelity hyperparameter optimization · 23 citations (OpenAlex)

Read the paper

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 the real validation set through the Newton-step approximation (vs No Validation) (ablation)AutoSimulate · LM-O object detectiontest mAP@0.50: 29.3 -> 36.1Improved
use linear approximation of the inner problem instead of exact quadratic (ablation)AutoSimulate · LM-O object detectiontest mAP@0.50: 36.1 -> 45.9Improved
use approximate quadratic instead of exact quadratic (ablation)AutoSimulate · LM-O object detectionsimulator training time (s): 23,193 -> 2,321Improved
use approximate quadratic instead of exact quadratic (ablation)AutoSimulate · LM-O object detectionimages generated: 8,950 -> 2,950Improved
use linear approximation instead of approximate quadratic (ablation)AutoSimulate · LM-O object detectionsimulator training time (s): 2,321 -> 30,477Hurt
freeze 98 of 112 layers of pretrained Yolo-spp (ablation)AutoSimulate · LM-O object detectiontest mAP@0.50: 45.9 -> 37.1Hurt
freeze 98 of 112 layers of pretrained Yolo-spp (ablation)AutoSimulate · LM-O object detectionsimulator training time (s): 30,477 -> 2,321Improved
freeze 104 of 112 layers (ablation)AutoSimulate · LM-O object detectiontest mAP@0.50: 45.9 -> 35.8Hurt
replace REINFORCE (LTS) with AutoSimulatesimulator optimizer · CLEVR segmentationimages generated: 3,750 -> 390Improved
replace Bayesian optimization with AutoSimulatesimulator optimizer · CLEVR segmentationtime: 43m -> 53mHurt
replace REINFORCE (LTS) with AutoSimulate (Linear)simulator optimizer · LM-O object detectiontest mAP@0.50: 37.2 -> 45.9Improved
replace REINFORCE (LTS) with AutoSimulate (Approx Quad)simulator optimizer · LM-O object detectionsimulator training time (s): 114,360 -> 2,321Improved

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