AI Paper Atlas

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

Multi-Domain Multi-Definition Landmark Localization for Small Datasets

David Ferman, Gaurav Bharaj

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 1 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 300W concurrent training (ablation)MDMD · AnimWebNME_ic: 6.88 -> 6.55Improved
add 300W concurrent training (ablation)MDMD · ArtFaceNME_ic: 4.46 -> 3.75Improved
add 300W concurrent training (ablation)MDMD · CariFaceNME_ic: 7.81 -> 5.85Improved
add 300W concurrent training (ablation)MDMD · PARENME_ic: 9.12 -> 8.59Improved
add LaPa concurrent trainingMDMD · COFWNME_ip: 4.82 -> 4.65Improved
add LaPa concurrent trainingMDMD · WFLWNME_ic: 4.06 -> 3.97Improved
use Laplacian log-likelihood instead of Euclidean loss (ablation)MDMD Single · COFWNME_ip: 4.90 -> 4.82Improved
use FLSG tokens instead of individual landmark tokens (ablation)MDMD Single · COFWNME_ip: 4.73 -> 4.82Hurt
use 12 FLSG groups instead of 5 (ablation)MDMD · WFLWNME_ic: 4.12 -> 4.06Improved
pretrain ViT instead of training from scratch (ablation)MDMD · COFWNME_ip: 13.97 -> 4.82Improved
use ViT instead of ResNet-50 backbone (ablation)MDMD · COFWNME_ip: 5.10 -> 4.82Improved
use MDMD joint training instead of sequential transfer learningMDMD · WFLW with LaPaNME_ic: 4.00 -> 3.97No clear effect

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