AI Paper Atlas

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

Competing Mutual Information Constraints with Stochastic Competition-Based Activations for Learning Diversified Representations

Konstantinos P. Panousis, Anastasios Antoniadis, Sotirios Chatzis

AAAI 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Tractable probabilistic models · 4 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
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-10, VGG-16error (%): 6.10 -> 6.01Improved
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-10, GoogLeNeterror (%): 4.26 -> 4.31Hurt
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-10, ResNet20error (%): 6.01 -> 5.94Improved
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-10, DenseNet40error (%): 4.99 -> 4.78Improved
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-100, VGG-16error (%): 24.54 -> 24.35Improved
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-100, GoogLeNeterror (%): 18.55 -> 19.00Hurt
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-100, ResNet20error (%): 28.13 -> 28.02Improved
replace ReLU activations with stochastic LWTA-2 and use IBP utility inferenceICP · CIFAR-100, DenseNet40error (%): 24.52 -> 24.44Improved
add stochastic rather than deterministic maximum-activation competition (ablation)ICP LWTA-2 · CIFAR-10, VGG-16error (%): 6.34 -> 6.23Improved
add stochastic rather than deterministic maximum-activation competition (ablation)ICP IBP & LWTA-2 · CIFAR-10, VGG-16error (%): 6.27 -> 6.01Improved
add IBP component-utility inference (ablation)ICP LWTA-2 · CIFAR-10, VGG-16error (%): 6.23 -> 6.01Improved
add stochastic rather than deterministic maximum-activation competition (ablation)ICP LWTA-4 · CIFAR-10, VGG-16error (%): 7.01 -> 6.85Improved

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