AI Paper Atlas

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

Prototype-based Dataset Comparison

Nanne van Noord

ICCV 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 4 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 number of prototypes K from 1024 to 8192 (ablation)ProtoSim · ImageNet val linear probeaccuracy: 54.7 -> 63.7 -> 64.8 (K=1024, 4096, 8192)Improved
train ProtoSim on ImageNet+PASS union instead of ImageNet only (ablation)ProtoSim · ImageNet val linear probeaccuracy: 64.8 -> 53.2Hurt
use PASS-pretrained backbone instead of ImageNet-pretrained DINO (ablation)ProtoSim · ImageNet val linear probeaccuracy: 64.8 -> 20.4Hurt
zero out the most frequent prototype of each class (ablation)ProtoSim on ImageNet · ImageNet per-class accuracy (top 100 classes)accuracy drop: 22.6 percentage points average differenceHurt
jointly learn prototypes across datasets to compare PASS and ImageNetProtoSim · PASS vs ImageNet case studyqualitativeImproved

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