AI Paper Atlas

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

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning

Konstantinos Almpanakis, Anna Kreshuk

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 0 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 diversity loss L_div on instance embedding table (ablation)IConE · Synthetic 2D GMMkNN accuracy (%): 57 -> 88Improved
add view-to-instance alignment loss L_vi (ablation)IConE · Synthetic 2D GMMkNN accuracy (%): 39 -> 88Improved
add view-view invariance loss L_vv (ablation)IConE · Synthetic 2D GMMkNN accuracy (%): 72 -> 88Improved
replace orthogonality loss with SIGReg (ablation)IConE · 2D MedMNIST, B=1top-1 accuracy (%): 59.6 -> 57.3Hurt
replace orthogonality loss with VCReg (ablation)IConE · 3D MedMNIST, B=32top-1 accuracy (%): 65.4 -> 67.9Mixed
increase number of views from 2 to 12 (ablation)IConE · 2D MedMNIST averagebalanced accuracy (%): 75.1 -> 74.8No clear effect
increase embedding init scale from 0.02 to 0.20 (ablation)IConE · 2D MedMNIST, B=1balanced accuracy (%): 74.3 -> 70.9No clear effect
use IConE instead of SimCLR/VICReg-style batch-dependent SSL3D linear/kNN · 3D MedMNIST k-NN-1, B=4k-NN balanced accuracy (%): 55.8 -> 63.6Improved
use IConE-Class instead of Cross-Entropysupervised learning · 2D MedMNIST, B=4top-1 balanced accuracy (%): 78.17 -> 82.42Improved
use IConE-Instance instead of SupConsupervised learning · 3D MedMNIST, B=1top-1 balanced accuracy (%): 59.49 -> 68.77Improved
use IConE-VCReg or SIGReg instead of defaultIConE · peak GPU memory N=100k, B=4GPU memory (GB): 637.2 -> 1.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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