AI Paper Atlas

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

Contrasting Quadratic Assignments for Set-Based Representation Learning

Artem Moskalev, Ivan Sosnovik, Volker Fischer, Arnold Smeulders

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations · 9 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 QARe regularizationTriplet · CUHK-03matching accuracy (%): 54.85 -> 58.48Improved
add QARe regularizationInfoNCE · CUHK-03matching accuracy (%): 57.87 -> 61.96Improved
add QARe regularizationNTLogistic · CUHK-03matching accuracy (%): 40.30 -> 43.48Improved
add QARe regularizationSparseCLR · CUHK-03matching accuracy (%): 53.03 -> 54.84Improved
add QARe regularizationSimCLR Conv-4 · CIFAR-10accuracy (%): 59.64 -> 61.54Improved
add QARe regularizationSimCLR ResNet-32 · tiny-ImageNetaccuracy (%): 23.44 -> 25.05Improved
add QARe regularizationSimCLR Conv-4 · tiny-ImageNetaccuracy (%): 21.15 -> 21.33No clear effect
add QARe regularizationSimCLR ResNet-32 · CIFAR-10accuracy (%): 76.45 -> 76.85No clear effect
add QARe regularizationSparseCLR ResNet-32 · tiny-ImageNetaccuracy (%): 25.87 -> 27.03Improved
add QARe regularizationSparseCLR Conv-4 · CIFAR-100accuracy (%): 32.04 -> 33.05Improved
replace log-sum-exp (InfoNCE-style) smoothing with sparsemax (SparseCLR)SimCLR ResNet-32 · CIFAR-10accuracy (%): 76.45 -> 70.37Hurt
replace log-sum-exp (InfoNCE-style) smoothing with sparsemax (SparseCLR)SimCLR ResNet-32 · tiny-ImageNetaccuracy (%): 23.44 -> 25.87Improved

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