AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Focus of Attention Improves Information Transfer in Visual Features

Matteo Tiezzi, Stefano Melacci, Alessandro Betti, Marco Maggini, Marco Gori

NeurIPS 2020 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Structured continuous-depth models

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
train with FOA density instead of uniformarchitecture D · SparseMNIST (test FOA)MI index: 0.103 -> 0.431Improved
train with FOA density instead of uniformarchitecture S · SparseMNIST (test FOA)MI index: 0.239 -> 0.486Improved
train with FOA density instead of uniformarchitecture D · Call (test FOA)MI index: 0.430 -> 0.582Improved
train with FOA density instead of uniformarchitecture S · Call (test FOA)MI index: 0.405 -> 0.405No clear effect
train with FOA density instead of uniformarchitecture S · Carpark (test FOA)MI index: 0.742 -> 0.675Hurt
train with FOA density instead of uniformarchitecture D · Carpark (test FOA)MI index: 0.678 -> 0.639Hurt
train with FOAW (window) density instead of uniformarchitecture D · Carpark (test FOA)MI index: 0.678 -> 0.768Improved
train with FOA density instead of uniformarchitecture DL · Call (test FOA)MI index: 0.246 -> 0.365Improved
use AVG instead of PLA temporal locality (ablation)architecture D, FOA · SparseMNIST (test FOA)MI index: 0.149 -> 0.321Improved
use VAR instead of AVG temporal locality (ablation)architecture D, FOA · SparseMNIST (test FOA)MI index: 0.321 -> 0.431Improved
use AVG instead of PLA temporal locality (ablation)architecture D, FOA · Carpark (test FOA)MI index: 0.458 -> 0.639Improved
use PLA instead of AVG temporal locality (ablation)architecture DL, FOA · Call (test FOA)MI index: 0.214 -> 0.365Improved

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