AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Deep Multiview Clustering by Contrasting Cluster Assignments

Jie Chen, Hua Mao, Wai Lok Woo, Xi Peng

ICCV 2023 · Learning theory and algorithms › Clustering · approach: Incomplete multi-view clustering · 162 citations (OpenAlex)

Read the paper

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 pretraining autoencoder stage before fine-tuning (ablation)CVCL · MSRC-v1ACC: 82.38 -> 97.62Improved
add pretraining stage on large datasets (ablation)CVCL · FashionACC: 99.16 -> 99.31No clear effect
add pretraining stage on BDGP (ablation)CVCL · BDGPACC: 99.12 -> 99.2No clear effect
add regularization term L_a against collapse (ablation)CVCL · MSRC-v1ACC: 55.34 -> 97.62Improved
add regularization term L_a (ablation)CVCL · MNIST-USPSACC: 59.84 -> 99.7Improved
add regularization term L_a (ablation)CVCL · Scene-15ACC: 25.04 -> 44.59Improved
add regularization term L_a (ablation)CVCL · FashionACC: 99.2 -> 99.31No clear effect
cluster-level contrast of cluster assignments versus other contrastive MVC methodsDSMVC, DCP, DSIMVC, MFL · MSRC-v1ACC: 93.33 -> 97.62Improved
cluster-level contrast versus ASR on small COIL-20ASR · COIL-20ACC: 80.9 -> 84.65Improved
vary alpha and beta loss weightsCVCL · MSRC-v1 vs FashionACCMixed

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