AI Paper Atlas

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

DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning

Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 169 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 cross-reference weights instead of equal weights in EMD (ablation)DeepEMD-FCN · miniImageNet 1-shot 5-wayaccuracy: 56.95 -> 61.13Improved
use EMD instead of dense connections with cross-reference weights (ablation)DeepEMD-FCN · miniImageNet 1-shot 5-wayaccuracy: 55.41 -> 61.13Improved
set EMD weights by K-means clustering instead of equal weights (K=10) (ablation)DeepEMD-FCN · miniImageNet 1-shot 5-wayaccuracy: 56.95 -> 56.25Hurt
set EMD weights by Mean-shift with auto bandwidth (ablation)DeepEMD-FCN · miniImageNet 1-shot 5-wayaccuracy: 56.95 -> 53.56Hurt
replace global-vector metric with EMD on local featuresDeepEMD-FCN · miniImageNet 1-shot 5-wayaccuracy: 63.08 -> 65.91Improved
add feature pyramid P_feat(5,2,1) (ablation)DeepEMD-FCN · miniImageNet 1-shot 5-wayaccuracy: 65.91 -> 66.50Improved
add image pyramid P_grid(5,3,2) (ablation)DeepEMD-Grid · miniImageNet 1-shot 5-wayaccuracy: 67.31 -> 67.83Improved
use a finer 6x6 grid instead of 3x3 (ablation)DeepEMD-Grid · miniImageNet 1-shot 5-wayaccuracy: 67.31 -> 63.61Hurt
sample more patches (9 to 25) (ablation)DeepEMD-Sampling · miniImageNet 1-shot 5-wayaccuracy: 68.09 -> 68.77Improved
add self-supervised rotation prediction in pre-training (ablation)DeepEMD-Sampling · miniImageNet 1-shot 5-wayaccuracy: 68.77 -> 69.17Improved
apply random rotation as data augmentation only (ablation)DeepEMD-Sampling · miniImageNet 1-shot 5-wayaccuracy: 68.77 -> 67.98Hurt
use OpenCV simplex solver instead of QPTH interior point at inferenceDeepEMD-FCN · EMD layer time 5x5 features 256 dimtime: 8.595 s -> 0.018 sImproved

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