AI Paper Atlas

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

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

Jing Xu, Xu Luo, Xinglin Pan, Yanan Li, Wenjie Pei, Zenglin Xu

NeurIPS 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 8 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 TCPR projection removalBaseline++ with ResNet-18 · miniImageNet 5-way 1-shotaccuracy: 54.23 ± 0.46 -> 58.67 ± 0.41Improved
Add TCPR projection removalS2M2 · tieredImageNet 5-way 1-shotaccuracy: 74.87 ± 0.43 -> 77.67 ± 0.41Improved
Add TCPR projection removalS2M2 · miniImageNet 5-way 5-shotaccuracy: 83.50 ± 0.29 -> 84.51 ± 0.27Improved
Estimate the task centroid from support and query features rather than base-neighbor features (ablation)TCPR · Meta-Dataset mini-test 5-way 1-shotaccuracy: 68.06 -> 69.52Improved
Estimate the task centroid from support features only rather than base-neighbor features (ablation)TCPR · Meta-Dataset mini-test 5-way 1-shotaccuracy: 68.06 -> 66.88Hurt
Estimate the task centroid from support and query features rather than base-neighbor features (ablation)TCPR · Meta-Dataset CUB 5-way 1-shotaccuracy: 51.87 -> 53.83Improved
Estimate the task centroid from support features only rather than base-neighbor features (ablation)TCPR · Meta-Dataset CUB 5-way 1-shotaccuracy: 51.87 -> 50.48Hurt
Add TCPR projection removalS2M2 · miniImageNet 2-way 1-shotaccuracy: 84.52 -> 88.39Improved
Add TCPR projection removalS2M2 · miniImageNet 10-way 1-shotaccuracy: 50.68 -> 52.80Improved
Use more base neighbors to approximate the task centroid (ablation)TCPR · Novel datasets with varying base-to-novel domain gapsaccuracyMixed

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