AI Paper Atlas

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

Null-sampling for Interpretable and Fair Representations

Thomas Kehrenberg, Myles Bartlett, Oliver Thomas, Novi Quadrianto

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 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
use cFlow (invertible encoder) instead of cVAE as colour sigma increasesnull-sampling · coloured MNISTaccuracyImproved
use null-sampled representations instead of raw images for a classifierCNN classifier · CelebA smiling, eta=0accuracy and DP diffImproved
use null-sampled representations at intermediate bias levelsCNN classifier · CelebA smiling, intermediate mixing factorsaccuracy vs DP diffMixed
use cFlow or cVAE representations instead of baselinesdownstream classifier · UCI Adult, eta 0 and 1accuracy and fairnessImproved
use the Ln2L mutual-information penalty instead of grey-scalingLn2L baseline · coloured MNIST with strong biasaccuracyHurt

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