AI Paper Atlas

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

Clustering by Maximizing Mutual Information Across Views

Kien Do, Truyen Tran, Svetha Venkatesh

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 64 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 the representation learning head and feature contrastive loss (ablation)C-head only · CIFAR10ACC: 66.9 -> 79.9Improved
add the representation learning head and feature contrastive loss (ablation)C-head only · STL10ACC: 61.2 -> 81.8Improved
add the representation learning head and feature contrastive loss (ablation)C-head only · ImageNet-DogsACC: 36.3 -> 46.1Improved
use log-of-dot-product critic instead of dot-product critic (ablation)CRLC probability contrastive loss · CIFAR10 and CIFAR20ACCImproved
use feature contrastive loss weight lambda2 of 10 instead of 0 (ablation)CRLC · CIFAR20ACCImproved
use too large feature contrastive weight (ablation)CRLC · CIFAR20ACCHurt
use MemoryBank implementation instead of SimCLR (ablation)CRLC · CIFAR10/20ACCMixed
use train and test sets for clustering on STL10 (ablation)CRLC · STL10ACC: 57.6 -> 81.8Improved
use train and test sets for clustering on CIFAR20 (ablation)CRLC · CIFAR20ACC: 43.4 -> 42.5No clear effect
use train and test sets for clustering on CIFAR10 (ablation)CRLC · CIFAR10ACC: 79.4 -> 79.9No clear effect
train both heads in second stage instead of only the C-head (ablation)two-stage CRLC · clusteringACCHurt
increase the number of negative samples (ablation)MemoryBank CRLC · CIFAR20ACCNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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