AI Paper Atlas

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

Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification

Sungwon Han, Sungwon Park, Sungkyu Park, Sundong Kim, Meeyoung Cha

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 33 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 consistency preserving loss Lcp (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 58.2 -> 81.0Improved
add weight normalization in the classifier (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 56.0 -> 81.0Improved
add temperature tau_c<1 in softmax (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 19.5 -> 81.0Improved
use Super-AND instead of AND for stage-1 embedding (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 73.9 -> 81.0Improved
use Super-AND instead of Lemniscate for stage-1 embedding (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 63.8 -> 81.0Improved
add pretrained Super-AND initialization vs random (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 58.6 -> 81.0Improved
replace k-means with second-stage refinement (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 38.3 -> 81.0Improved
replace hierarchical clustering with second-stage refinement (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 49.9 -> 81.0Improved
separate embedding pretraining and class assignment into two stages instead of joint (ablation)Two-stage model · CIFAR-10 (unsupervised)accuracy: 68.4 -> 81.0Improved
use two-stage model instead of IICTwo-stage model · CIFAR-10 (unsupervised)accuracy: 61.7 -> 81.0Improved
use two-stage model instead of IICTwo-stage model · CIFAR-100accuracy: 20.3 -> 28.1Improved
add our pretraining to Mean TeacherMean Teacher · CIFAR-10 (4000 labels)accuracy: 84.2 -> 88.0Improved

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