AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Information Dropout: Learning Optimal Representations Through Noisy Computation

Alessandro Achille, Stefano Soatto

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 407 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 Gaussian latent with Information Dropout layer in a VAEVAE · VAE test set, k=1variational lower bound: -98.8 -> -100.0No clear effect
replace Gaussian latent with Information Dropout layer in a VAEVAE · VAE test set, k=3variational lower bound: -98.7 -> -99.1No clear effect
use Information Dropout instead of binary dropoutfully connected net on MNIST and All-CNN-32 on CIFAR-10 · MNIST / CIFAR-10classification errorImproved
use adaptive noise instead of constant log-normal noise with same variance (ablation)Information Dropout · MNISTclassification errorImproved
increase beta (ablation)Information Dropout, All-CNN-32 · Occluded CIFARmain task test errorImproved
increase beta too far (ablation)Information Dropout, All-CNN-32 · CIFAR-10 (25% filters)test errorHurt

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