AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning

Oscar Skean, Aayush Dhakal, Nathan Jacobs, Luis G Sanchez Giraldo

ECCV 2024 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 8 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
increase FroSSL views from 2 to 8 (ablation)FroSSL · STL-10 linear probetop-1 accuracy: 87.3 -> 90.9Improved
increase FroSSL views from 2 to 8 (ablation)FroSSL · Tiny ImageNet linear probetop-1 accuracy: 44.2 -> 45.3Improved
increase FroSSL views from 2 to 8 (ablation)FroSSL · CIFAR-10/100top-1 accuracyNo clear effect
increase FroSSL views from 2 to 8 (ablation)FroSSL · ImageNet-1k 10% datatop-1 accuracy: 33.4 -> 38.2Improved
add log to Frobenius norm term (ablation)FroSSL (2 views) · Average over 5 datasetsaccuracy: 69.7 -> 74.6Improved
use strong instead of weak augmentations (ablation)FroSSL (2 views) · Tiny ImageNettop-1 accuracy: 39.4 -> 44.2Improved
FroSSL vs other dimension-contrastive methods under weak augmentationsFroSSL · Tiny ImageNettop-1 accuracy: VICReg 18.1, MMCR 24.2 vs FroSSL 39.4Improved
use FroSSL (2 views) instead of other SSL methodsFroSSL · Average over 5 datasetsaccuracy: 74.7 (Barlow Twins) vs 74.6No clear effect
use FroSSL in low data regimeFroSSL · ImageNet-1k 10% datatop-1 accuracy: 31.1 (SimCLR) -> 33.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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