AI Paper Atlas

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

Boosting Few-Shot Visual Learning With Self-Supervision

Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Perez, Matthieu Cord

ICCV 2019 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 447 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 rotation prediction self-supervision (ablation)Cosine Classifier (WRN-28-10) · MiniImageNet 5-way 1-shotaccuracy (%): 61.09 -> 62.93Improved
add rotation prediction self-supervision (ablation)Prototypical Networks (WRN-28-10) · MiniImageNet 5-way 5-shotaccuracy (%): 68.72 -> 72.13Improved
add rotation prediction self-supervision (ablation)Cosine Classifier (WRN-28-10) · CIFAR-FS 5-way 1-shotaccuracy (%): 71.83 -> 73.62Improved
add rotation prediction self-supervision (ablation)Prototypical Networks (WRN-28-10) · CIFAR-FS 5-way 5-shotaccuracy (%): 81.79 -> 81.25Hurt
add rotation prediction self-supervision (ablation)Cosine Classifier (WRN-28-10) · tiered-MiniImageNet 5-way 1-shotaccuracy (%): 70.04 -> 70.53Improved
add relative patch location self-supervision (ablation)Cosine Classifier (WRN-28-10) · MiniImageNet 5-way 1-shotaccuracy (%): 58.43 -> 60.71Improved
add rotation augmentation to CC baseline (ablation)Cosine Classifier (Conv-4-64) · MiniImageNet 5-way 5-shotaccuracy (%): 71.13 -> 70.89Hurt
add rotation augmentation to CC baseline (ablation)Cosine Classifier (WRN-28-10) · MiniImageNet 5-way 1-shotaccuracy (%): 58.59 -> 61.09Improved
add auxiliary patch classification loss to CC baseline (ablation)Cosine Classifier (WRN-28-10) · MiniImageNet 5-way 1-shotaccuracy (%): 58.59 -> 58.43Hurt
add unlabeled MiniImageNet images with self-supervision (5% labels) (ablation)CC+rot (WRN-28-10) · MiniImageNet 5% labels 5-way 1-shotaccuracy (%): 43.60 -> 47.25Improved
add unlabeled tiered-MiniImageNet images (5% labels) (ablation)CC+rot (WRN-28-10) · MiniImageNet 5% labels 5-way 1-shotaccuracy (%): 43.60 -> 46.95Improved
add unlabeled tiered-MiniImageNet images (full labels)CC+rot (WRN-28-10) · MiniImageNet 5-way 1-shotaccuracy (%): 62.93 -> 63.77Improved

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