AI Paper Atlas

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

Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment

Jiahao Xia, Min Gang Xu, Wenjian Huang, Jianguo Zhang, Haimin Zhang, Chunxia Xiao

IJCV 2025 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 2 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
train on multiple datasets instead of a single datasetTUFA (ViT-S/8) · WFLW (full set)NME: 4.23 -> 3.93Improved
train on multiple datasets instead of a single datasetTUFA (ViT-S/8) · 300W (full set)NME: 3.23 -> 2.95Improved
train on multiple datasets instead of a single datasetTUFA (ViT-S/8) · COFWNME: 3.40 -> 3.07Improved
train on multiple datasets instead of a single datasetTUFA (ViT-S/8) · COFW68 (cross-dataset)NME: 4.11 -> 3.70Improved
train on multiple datasets instead of a single datasetTUFA (ViT-S/8) · Masked 300W (full set)NME: 7.67 -> 5.58Improved
train on multiple datasets instead of a single datasetTUFA (ViT-S/8) · MERL-RAV (full set)NME_box: 1.55 -> 1.54No clear effect
add COFW as a second training dataset to 300W (ablation)TUFA (ViT-S/8) · 300WNME: 3.23 -> 3.14Improved
add WFLW as a third training dataset (ablation)TUFA (ViT-S/8) · 300WNME: 3.14 -> 3.08Improved
add MERL-RAV as a fourth training dataset (ablation)TUFA (ViT-S/8) · 300WNME: 3.08 -> 2.95Improved
add semantic alignment embeddings to affine-aligned mean shapes (ablation)TUFA (ViT-S/8) · 300WNME: 3.42 -> 2.95Improved
add semantic alignment embeddings (ablation)TUFA (ViT-S/8) · 300W-privateNME: 4.08 -> 3.40Improved
use unified plane with structure prompts instead of multi-task learning (ablation)TUFA (ViT-S/8) · MERL-RAVNME_box: 1.94 -> 1.54Improved

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