AI Paper Atlas

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

DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers

Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen

CVPR 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification

Check 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 local feature representations with EMD matchingfew-shot image classification · miniImageNet 1-shot 5-wayaccuracy: 63.08 -> 65.91Improved
Use local feature representations with EMD matchingfew-shot image classification · miniImageNet 1-shot 5-wayaccuracy: 62.52 -> 65.91Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · miniImageNet 5-shot 5-wayaccuracy: 80.51 -> 82.41Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · tieredImageNet 1-shot 5-wayaccuracy: 68.50 -> 71.16Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · tieredImageNet 5-shot 5-wayaccuracy: 84.28 -> 86.03Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · FC100 1-shot 5-wayaccuracy: 45.10 -> 46.47Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · FC100 5-shot 5-wayaccuracy: 57.6 -> 63.22Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · CUB 1-shot 5-wayaccuracy: 71.87 -> 75.65Improved
Use DeepEMD instead of the strongest listed baselinefew-shot image classification · CUB 5-shot 5-wayaccuracy: 85.08 -> 88.69Improved
Add cross-reference weighting to EMD node weights (ablation)DeepEMD · miniImageNet 1-shot 5-wayaccuracy: 56.95 -> 61.13Improved
Replace cross-reference weights with K-means weights (ablation)DeepEMD · miniImageNet 1-shot 5-wayaccuracy: 61.13 -> 56.25Hurt
Replace cross-reference weights with mean-shift weights (ablation)DeepEMD · miniImageNet 1-shot 5-wayaccuracy: 61.13 -> 53.56Hurt

Later papers that compared with this method

25 later accepted papers report DeepEMD as a baseline in their results tables; 20 of them report a better number on most of the results they share with it.

17 more not listed.

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