AI Paper Atlas

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

Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training

Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

ICCV 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 199 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
use embedded class models with learned prototypes instead of mean prototypesPrototypical Networks · miniImageNet 5-way 1-shot (C64)accuracy (%): 43.88 -> 49.07Improved
use embedded class models, train with 1-shot and test 5-shotPrototypical Networks · miniImageNet 5-way (C64)accuracy (%): 58.33 -> 64.98Improved
use embedded class models instead of mean prototypesPrototypical Networks · tieredImageNet 5-way 1-shot (C64)accuracy (%): 41.36 -> 48.19Improved
use embedded class models instead of mean prototypesPrototypical Networks · CIFAR-FS 5-way 1-shot (C64)accuracy (%): 50.74 -> 55.14Improved
use embedded class models when train and test shots match at 5Prototypical Networks · miniImageNet 5-way 5-shot (C64)accuracy (%): 65.49 -> 65.73No clear effect
use embedded class models when train and test shots match at 5Prototypical Networks · tieredImageNet 5-way 5-shot (C64)accuracy (%): 65.51 -> 65.50No clear effect
lift class identity dimension to 2x the embedding dimension (ablation)Embedded class models · miniImageNet 5-way 1-shot (C64)accuracy (%): 49.07 -> 51.46Improved
increase class identity dimension from 2x to 10x (ablation)Embedded class models · miniImageNet 5-way 1-shot (C64)accuracy (%): 51.46 -> 51.32No clear effect
use 2x class identity dimension (ablation)Embedded class models (ResNet-12) · tieredImageNet 5-way 1-shotaccuracy (%): 63.99 -> 66.87Improved
use 2x class identity dimension (ablation)Embedded class models (ResNet-12) · miniImageNet 5-wayaccuracy (%): 1-shot 59.00 -> 60.64; 5-shot 77.46 -> 77.02Mixed
widen ResNet-12 filters to (64,160,320,640) (ablation)Embedded class models · miniImageNet 5-way 1-shotaccuracy (%): 59.00 -> 59.04No clear effect
replace ADAM with SGD (ablation)Embedded class models (ResNet-12) · miniImageNet 5-wayaccuracy (%): 1-shot 59.41 -> 59.00; 5-shot 76.75 -> 77.46; 10-shot 81.33 -> 82.33Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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