AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Learning from Bad Data via Generation

Tianyu Guo, Chang Xu, Boxin Shi, Chao Xu, Dacheng Tao

NeurIPS 2019 · Learning theory and algorithms › Optimal transport · approach: Wasserstein losses for generative models · 3 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 worst-case generator training to classifier (Ours vs Classifier)classifier · CIFAR-10 IF=20accuracy (%): 81.51 -> 81.94Improved
add worst-case generator (Ours vs Classifier)classifier · MNIST IF=100accuracy (%): 89.77 -> 92.67Improved
add worst-case generator (Ours vs Classifier)classifier · FMNIST IF=100accuracy (%): 79.89 -> 83.06Improved
add DAGAN augmentationclassifier · CIFAR-10 IF=10accuracy (%): 85.57 -> 77.82Hurt
add Triple GAN generatorclassifier · CIFAR-10 IF=10accuracy (%): 85.57 -> 83.06Hurt
add Ours to classifier on balanced dataclassifier · MNIST IF=1accuracy (%): 99.35 -> 99.42Improved
add Ours to classifier on balanced dataclassifier · CIFAR-10 IF=1accuracy (%): 93.04 -> 93.01No clear effect
use ResNet-101 instead of VGG16 as classifier in OursOurs · CIFAR-10 G(0.2)accuracy (%): 85.02 -> 85.87Improved
replace Mixup with Ours as augmentationMixup · CIFAR-10 reducedaccuracy (%): 83.91 -> 84.60Improved
replace standard GAN with Ours as generator (FID)GAN · CIFAR-10 IF=10FID: 37.96 -> 26.10Improved
remove BN and WD (classifier only), Ours vs classifier (ablation)classifier · Reduced CIFAR-10accuracy (%): 71.85 -> 75.42Improved
remove BN from Ours (accuracy with BN+WD to No BN) (ablation)Ours · Reduced CIFAR-10accuracy (%): 84.60 -> 78.01Hurt

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