AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Ranking Distance Calibration for Cross-Domain Few-Shot Learning

Pan Li, Shaogang Gong, Chengjie Wang, Yanwei Fu

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 70 citations (OpenAlex)

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
Calibrate pairwise distances by reciprocal-neighbor re-ranking using task support and query examplesNPC with ResNet10 · 5-way 1-shot, average over 8 target domainsaccuracy: 39.72 -> 48.65Improved
Calibrate pairwise distances by reciprocal-neighbor re-ranking using task support and query examplesNPC with ResNet10 · 5-way 5-shot, average over 8 target domainsaccuracy: 57.42 -> 60.06Improved
Fine-tune the representation by mapping its distance distribution toward calibrated distancesResNet10 CD-FSL representation · 5-way 1-shot, average over 8 target domainsaccuracy: 46.25 -> 51.53Improved
Fine-tune the representation by mapping its distance distribution toward calibrated distancesResNet10 CD-FSL representation · 5-way 5-shot, average over 8 target domainsaccuracy: 64.68 -> 63.70Mixed
Add the task-adaptive nonlinear subspace to RDC (ablation)RDC · 5-way 1-shot, average over 8 target domainsaccuracy: 47.71 -> 48.65Improved
Add the task-adaptive nonlinear subspace to RDC (ablation)RDC · 5-way 5-shot, average over 8 target domainsaccuracy: 58.97 -> 60.06Improved
Add the task-adaptive nonlinear subspace to RDC-FT (ablation)RDC-FT · 5-way 1-shot, average over 8 target domainsaccuracy: 51.03 -> 51.53Improved
Add the task-adaptive nonlinear subspace to RDC-FT (ablation)RDC-FT · 5-way 5-shot, average over 8 target domainsaccuracy: 62.91 -> 63.70Improved
Use a tanh nonlinear subspace rather than the original space or tested KPCA kernels (ablation)RDC · 5-way 1-shot, average over 8 target domainsaccuracy: 47.41 -> 48.36Improved
Use a tanh nonlinear subspace rather than the original space (ablation)RDC · 5-way 5-shot, average over 8 target domainsaccuracy: 59.09 -> 59.83Improved
Apply attention weighting to reciprocal-neighbor distances during fine-tuning (ablation)RDC-FT · 5-way 1-shot, average over 8 target domainsaccuracy: 51.09 -> 51.53Improved
Apply attention weighting to reciprocal-neighbor distances during fine-tuning (ablation)RDC-FT · 5-way 5-shot, average over 8 target domainsaccuracy: 63.16 -> 63.70Improved

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