AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy

Cheng-Yaw Low, Heejoon Koo, Jaewoo Park, Meeyoung Cha

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 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 dual-margin penalization over base margin only (ablation)TaxoNet · AA-Centralmacro recall: 63.91 -> 67.59Improved
add norm-guided oversampling over no oversampling (ablation)TaxoNet (dual-margin) · AA-Centralmacro recall: 67.59 -> 69.48Improved
norm-guided instead of random oversampling selection (ablation)TaxoNet (dual-margin) · AA-Centralmacro recall: 67.56 -> 69.48Improved
random-selection oversampling instead of none (ablation)TaxoNet (dual-margin) · AA-Centralmacro recall: 67.59 -> 67.56No clear effect
add power-based regularization (ablation)TaxoNet (B, E) · AA-Centralmacro recall: 69.48 -> 72.90Improved
add power-based regularization (ablation)TaxoNet (B, E) · iNat-Plantaemacro recall: 81.87 -> 83.21Improved
add power-based regularization (ablation)TaxoNet (B, E) · AA-Eastrank-1 accuracy: 84.53 -> 84.32Hurt
TaxoNet versus LDAM, strongest baselineAA-Central · AA-Centralrank-1 accuracy: 92.31 -> 91.92Hurt
TaxoNet versus LDAM on tail genus classesAA-Central · AA-Central genus tailmacro recall: 44.18 -> 57.06Improved
TaxoNet versus LDAM on head genus classesAA-Central · AA-Central genus headmacro recall: 94.13 -> 92.37Hurt
TaxoNet versus LDAM under regional shiftAA-Central model on AA-East · AA-East transferrank-1 accuracy: 49.26 -> 52.13Improved
TaxoNet versus LDAM in open-set rejectionAA-Central · Open-set AA-CentralTNR: 88.59 -> 91.28Improved

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