AI Paper Atlas

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

RELAX: Representation Learning Explainability

Kristoffer Wickstrøm, Daniel J. Trosten, Sigurd Løkse, Ahcène Boubekki, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen

IJCV 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 17 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
use RELAX instead of Saliencysupervised ResNet · Pointing game (VOC)pointing game: 67.1 -> 72.6Improved
use RELAX instead of SaliencySimCLR · Pointing game (COCO)pointing game: 75.9 -> 85.2Improved
use RELAX instead of SaliencySwAV · Relevance rank (VOC)relevance rank: 40.9 -> 52.4Improved
add uncertainty filtering (U-RELAX) to RELAX (ablation)supervised features · Monotonicitymonotonicity: 18.3 -> 23.6Improved
add uncertainty filtering (U-RELAX) to RELAX (ablation)SwAV features · Monotonicitymonotonicity: 21.3 -> 18.3Hurt
add uncertainty filtering (U-RELAX) to RELAX (ablation)SimCLR · Pointing game (VOC)pointing game: 68.7 -> 68.6No clear effect
add uncertainty filtering (U-RELAX) to RELAX (ablation)supervised features · Relevance rank (VOC)relevance rank: 56.4 -> 52.4Hurt
use gamma 1.0 instead of 0.95 in U-RELAX (median) (ablation)U-RELAX · Monotonicity, supervisedmonotonicity: 17.9 -> 23.6Improved
use median instead of mean aggregation in U-RELAX (gamma 1.0) (ablation)U-RELAX · Monotonicity, supervisedmonotonicity: 23.2 -> 23.6Improved
mask with zeros instead of Gaussian noise (ablation)RELAX · Pointing game (VOC), SimCLRpointing game: 66.6 -> 68.7Improved
mask with zeros instead of Gaussian noise (ablation)RELAX · Pointing game (COCO), SwAVpointing game: 85.1 -> 84.7No clear effect

Later papers that compared with this method

1 later accepted paper reports RELAX as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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