AI Paper Atlas

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

Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport

Dan dan Guo, Long Tian, He Zhao, Mingyuan Zhou, Hongyuan Zha

NeurIPS 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 12 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 hierarchical OT adaptive weights instead of top-k Euclidean selectionFree-Lunch · miniImageNet 5-way 1-shotaccuracy: 68.57 -> 69.04Improved
add hierarchical OT adaptive weights instead of top-k Euclidean selectionFree-Lunch · CUB 5-way 1-shotaccuracy: 79.56 -> 81.23Improved
add hierarchical OT adaptive weightsFree-Lunch · tieredImageNet 5-way 5-shot (ResNet12)accuracy: 85.56 -> 87.46Improved
add low-level OT adaptive cost instead of cosine cost to class mean (ablation)H-OT · miniImageNet 5-way 1-shotaccuracy: 68.82 -> 69.04Improved
add low-level OT adaptive cost instead of cosine cost to class mean (ablation)H-OT · CUB 5-way 1-shotaccuracy: 81.01 -> 81.23Improved
add low-level OT adaptive cost instead of Euclidean cost to class mean (ablation)H-OT · tieredImageNet 5-way 1-shotaccuracy: 75.31 -> 75.91Improved
use sample-weighted class mean in cost function (ablation)H-OT · miniImageNet 5-way 1-shotaccuracy: 68.82 -> 68.78No clear effect
use cosine instead of Euclidean cost with high-level OT only (ablation)H-OT · CUB 5-way 1-shotaccuracy: 80.29 -> 81.01Improved
use high-level OT with fixed cost instead of Free-Lunch top-k (ablation)H-OT · miniImageNet 5-way 1-shotaccuracy: 68.57 -> 68.79Improved
swap WRN28+RTloss for weaker backbones (Conv4, ResNet18)H-OT vs Free-Lunch · miniImageNet 5-way 1-shotaccuracy: 61.50 -> 62.61 (ResNet18)Improved
cross-domain base from CIFAR-FS to novel CUBH-OT · CIFAR-FS to CUBaccuracyImproved

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