AI Paper Atlas

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

Dataset Bias in Few-Shot Image Recognition

Shuqiang Jiang, Yaohui Zhu, Chenlong Liu, Xinhang Song, Xiangyang Li, Weiqing Min

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 28 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 ResNet-12 backbone instead of CNN-4ProtoNet (PN) · five Mini datasets, 5-way 1-shotaccuracy gain: 8.83%Improved
use ResNet-12 backbone instead of CNN-4Relation Network (RN) · five Mini datasets, 5-way 1-shotaccuracy gain: 3.53%Improved
use ResNet-12 instead of CNN-4all methods · MiniCharacteraverage accuracy gain: 4.21%Improved
use ResNet-12 instead of CNN-4all methods · MiniPlacesaverage accuracy gain: 8.53%Improved
lower image complexity of the dataset (MiniCharacter vs MiniImagenet) (ablation)PN · 5-way 1-shot, CNN-4accuracy (%): 49.42 -> 86.17Improved
MiniPlaces instead of MiniFood (similar complexity, larger intra-inter consistency gap) (ablation)all methods · 5-way 1-shot, CNN-4 and ResNet-12average accuracy gain: 6.8% (CNN-4), 7.8% (ResNet-12)Improved
use DEMD instead of PN on fine-grained MiniFood (ablation)DEMD · MiniFood 5-way 1-shot, CNN-4accuracy (%): 41.41 -> 50.70Improved
use MetaOpt instead of PN on MiniPlaces (ablation)MetaOpt · MiniPlaces 5-way 1-shot, CNN-4accuracy (%): 49.00 -> 55.74Improved
initialize classifier with prototypes (Proto-MAML instead of MAML) (ablation)Proto-MAML · MiniCharacter, ResNet-12accuracy (%): 85.65 -> 94.24Improved
more instances per base category (10 to 1,200) with relevant novel categories (ablation)base categories (LTED) · SG-(L;L) 5-way 1-shotaccuracy: improvement fast from 10 to 200 samples, slower afterImproved
more instances per base category with irrelevant novel categories (ablation)base categories (LTED) · SG-(L;AI) 5-way 1-shotaccuracy: no significant gain after 100 samples per categoryMixed
add irrelevant additional base categories (AROT) to LTED base for LTED novel (ablation)additional base categories · CG-(L,AO;L) 5-way 1-shotaccuracy: improves at first, then dropsMixed

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