AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

Xu Ji, Joao F. Henriques, Andrea Vedaldi

ICCV 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 815 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 auxiliary overclustering head (ablation)IIC · STL10 (unsupervised clustering)accuracy (%): 43.8 -> 59.6Improved
use 5 sub-heads instead of 1 (ablation)IIC · STL10 (unsupervised clustering)accuracy (%): 57.6 -> 59.6Improved
repeat each sample 5 times per batch instead of once (ablation)IIC · STL10 (unsupervised clustering)accuracy (%): 47.0 -> 59.6Improved
use the unlabelled data subset of STL10 (ablation)IIC · STL10 (unsupervised clustering)accuracy (%): 49.9 -> 59.6Improved
add entropy coefficient 1.5 to the lossIIC · Potsdam-3 and COCO-Stuff-3 segmentationpixel accuracy (%): 1.2%-3.2%Improved
reduce labels by 90% (5000 to 500) in semi-supervised overclusteringIIC overclustering · STL10 (semi-supervised)accuracy (%): ~10% dropHurt
use the auxiliary overclustering head with distractor-containing unlabelled dataIIC · STL10 (unsupervised clustering)accuracy (%): 43.8 -> 59.6Improved

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