AI Paper Atlas

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

Semantic-Guided Fine-Tuning of Foundation Model for Long-Tailed Visual Recognition

Yufei Peng, Yonggang Zhang, Yiu‐ming Cheung

IJCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 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 SG-Adapter (ablation)baseline without SG · CIFAR-100-LT (imbalance 10)top-1 accuracy: 84.9 -> 86.0Improved
add SG-Adapter (ablation)baseline without SG · CIFAR-100-LT (imbalance 50)top-1 accuracy: 83.1 -> 84.1Improved
add SG-Adapter (ablation)baseline without SG · CIFAR-100-LT (imbalance 100)top-1 accuracy: 81.7 -> 81.9Improved
add SG-Adapter (ablation)baseline without SG · ImageNet-LTtop-1 accuracy: 78.3 -> 78.4No clear effect
add text-average initialization (Init) (ablation)SG-Adapter · CIFAR-100-LT (imbalance 100)top-1 accuracy: 81.9 -> 82.5Improved
add compensation factor (CF) (ablation)SG + Init · CIFAR-100-LT (imbalance 100)top-1 accuracy (tail): 77.2 -> 78.3Improved
add compensation factor (CF) (ablation)SG + Init · Places-LTtop-1 accuracy (tail): 52.2 -> 53.2Improved
add feature interchange technique (FIT) (ablation)SG + Init + CF · CIFAR-100-LT (imbalance 100)top-1 accuracy (tail): 78.3 -> 80.0Improved
add feature interchange technique (FIT) (ablation)SG + Init + CF · ImageNet-LTtop-1 accuracy (head): 81.2 -> 82.1Improved
add feature interchange technique (FIT) (ablation)SG + Init + CF · iNaturalist 2018top-1 accuracy: 80.9 -> 80.9No clear effect
add feature interchange technique (FIT) (ablation)SG + Init + CF · Places-LTtop-1 accuracy (medium): 53.3 -> 52.8Hurt
add compensation factor (CF) (ablation)CE · CIFAR-100-LT (imbalance 100)top-1 accuracy (tail): 11.5 -> 24.7Improved

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