AI Paper Atlas

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

Mixture-Based Feature Space Learning for Few-Shot Image Classification

Arman Afrasiyabi, Jean-François Lalonde, Christian Gagné

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 107 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 assignment loss La only to the baseline (ablation)MixtFSL (ResNet-12) · miniImageNet validation 1-shotaccuracy: 56.55 -> 56.52No clear effect
add diversity loss Ld with stop-gradient (initial training) (ablation)MixtFSL (ResNet-12) · miniImageNet validation 1-shotaccuracy: 56.52 -> 57.88Improved
add diversity loss Ld with stop-gradient (initial training) (ablation)MixtFSL (ResNet-18) · miniImageNet validation 1-/5-shotaccuracy: 72.67 -> 69.43Mixed
add progressive following stage with Lpf (ablation)MixtFSL (ResNet-12) · miniImageNet validation 5-shotaccuracy: 73.94 -> 76.09Improved
remove stop-gradient from diversity loss (ablation)MixtFSL · miniImageNet base classescomponent collapseHurt
increase initial components per class from 5 to 10 (ablation)MixtFSL (ResNet-12) · miniImageNet 1-shotaccuracy: 62.29 -> 64.01Improved
increase initial components per class from 15 to 20 (ablation)MixtFSL (ResNet-12) · miniImageNet 1-shotaccuracy: 63.98 -> 63.91No clear effect
use negative margin instead of positive margin (ablation)MixtFSL (ResNet-12) · miniImageNet 1-shotaccuracy: 63.57 -> 63.98No clear effect
use margin m=-0.02 instead of m=+0.01 (ablation)MixtFSL (ResNet-12) · miniImageNet validation 5-shotaccuracy: 77.43 -> 80.38Improved
use temperature tau=0.05 instead of tau=1 (ablation)MixtFSL (ResNet-12, ResNet-18) · miniImageNet validationaccuracyImproved
replace centroid alignment features with MixtFSL featuresCentroid Alignment (ResNet-12) · miniImageNet 5-shotaccuracy: 80.96 -> 82.45Improved
replace centroid alignment features with MixtFSL featuresCentroid Alignment (ResNet-18) · tieredImageNet 5-shotaccuracy: 85.97 -> 85.57Hurt

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