AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification

Nikita Dvornik, Cordelia Schmid, Julien Mairal

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 127 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
select features with SUR instead of concatenating all domain features (ablation)8 ResNet18 multi-domain set · Meta-Dataset ImageNetaccuracy: 19.5 -> 56.0Improved
select features with SUR instead of concatenating all domain features (ablation)8 ResNet18 multi-domain set · Meta-Dataset Aircraftaccuracy: 33.7 -> 85.7Improved
select features with SUR instead of single ImageNet extractor (ablation)ImageNet-F · Meta-Dataset Aircraftaccuracy: 50.4 -> 85.7Improved
select features with SUR instead of single ImageNet extractor (ablation)ImageNet-F · Meta-Dataset Fungiaccuracy: 39.1 -> 62.8Improved
select features with SUR instead of union-trained extractor (ablation)Union-F · Meta-Dataset CIFAR 100accuracy: 39.5 -> 54.5Improved
select features with SUR instead of ImageNet extractor on ImageNet-like data (ablation)ImageNet-F · Meta-Dataset CIFAR 10accuracy: 66.3 -> 64.6Hurt
use parametric network family (FiLM) instead of 8 separate networksSUR · Meta-Dataset ImageNet-like vs Fungiaccuracy: ImageNet 56.3 -> 56.4; Fungi 63.1 -> 48.2Mixed
merge datasets into 3 visual domains (SUR-merge)SUR · Meta-Dataset Aircraftaccuracy: 85.4 -> 90.1Improved
merge datasets into 3 visual domains (SUR-merge)SUR · Meta-Dataset MNISTaccuracy: 94.3 -> 90.8Hurt
remove Birds, Textures, VGG Flower extractors (SUR 5/8) (ablation)SUR · Meta-Dataset Traffic Signaccuracy: 66.1 -> 63.6Hurt
remove Birds, Textures, VGG Flower extractors (SUR 5/8) (ablation)SUR · Meta-Dataset MNISTaccuracy: 91.2 -> 92.5Improved
add SUR selection over last 6 layersCls ResNet12 · mini-ImageNet 5-shotaccuracy: 76.28 -> 79.25Improved

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