AI Paper Atlas

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

JEM++: Improved Techniques for Training JEM

Xiulong Yang, Shihao Ji

ICCV 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 16 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 proximity constraint (Proximal SGLD) (ablation)JEM++ · CIFAR10 ablation (M=10, N=5)accuracy (%): 92.9 -> 93.5Improved
add proximity constraint (ablation)JEM++ · CIFAR10 ablation (M=10, N=5)FID: 36.0 -> 37.1Hurt
use SGD with large learning rate instead of Adam (ablation)JEM++ · CIFAR10 ablation (M=10, N=5)FID: 42.7 -> 37.1Improved
use SGD instead of Adam (ablation)JEM++ · CIFAR10 ablation (M=10, N=5)accuracy (%): 92.5 -> 93.5Improved
add informative initialization with batch norm (ablation)JEM++ · CIFAR10 ablation (M=10, N=5)accuracy (%): 88.6 -> 93.5Improved
enable batch norm with informative init (ablation)JEM++ · CIFAR10 ablation (M=10, N=5)accuracy (%): 91.1 -> 93.5Improved
increase SGLD steps M from 5 to 10JEM++ · CIFAR10accuracy (%): 91.1 -> 93.5Improved
increase M from 10 to 20JEM++ · CIFAR10accuracy (%): 93.5 -> 94.1Improved
increase M from 10 to 20JEM++ · CIFAR10per-epoch speedup vs JEM: 1.49x -> .93xHurt
increase inner steps N from 5 to 20JEM++ (M=10) · CIFAR10minutes per epoch: 20.1 -> 20.4No clear effect
replace JEM with JEM++ (M=10)JEM (K=20) · CIFAR100accuracy (%): 72.2 -> 74.5Improved
replace JEM with JEM++ (M=10)JEM (K=20) · SVHNaccuracy (%): 96.7 -> 96.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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