AI Paper Atlas

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

Stake the Points: Structure-Faithful Instance Unlearning

Kiseong Hong, JungKyoo Shin, Eunwoo Kim

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 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 structure-aware alignment (ablation)STRUCTGUARD · CIFAR-10 (k=256)Atest accuracy: 37.75 -> 56.32Improved
add structure-aware alignment (ablation)STRUCTGUARD · CIFAR-100 (k=256)Atest accuracy: 51.49 -> 56.91Improved
add structure-aware regularization (ablation)STRUCTGUARD · CIFAR-10 (k=256)Atest accuracy: 55.01 -> 56.32Improved
add classifier regularization (ablation)STRUCTGUARD · CIFAR-10 (k=256)Atest accuracy: 54.08 -> 56.32Improved
add structure-aware regularization (ablation)STRUCTGUARD · CIFAR-100 (k=256)Atest accuracy: 55.86 -> 56.91Improved
add classifier regularization (ablation)STRUCTGUARD · CIFAR-100 (k=256)Atest accuracy: 56.42 -> 56.91Improved
use LLM-attribute semantic anchors instead of visual prototype anchors (ablation)STRUCTGUARD · CIFAR-10 (k=256)Atest accuracy: 48.78 -> 56.32Improved
use LLM-attribute semantic anchors instead of visual prototype anchors (ablation)STRUCTGUARD · ImageNet-1K (k=256)Atest accuracy: 40.95 -> 41.15Improved
use cosine similarity instead of MSE for alignment (ablation)STRUCTGUARD · CIFAR-10 (k=256)Atest accuracy: 43.80 -> 56.32Improved
use cosine similarity instead of Wasserstein distance for alignment (ablation)STRUCTGUARD · CIFAR-100 (k=256)Atest accuracy: 55.51 -> 56.91Improved
StructGuard (structure-preserving anchors) vs L2ULStructGuard vs L2UL · ImageNet-1K (k=256)Atest accuracy: 31.19 -> 41.15Improved
StructGuard vs ORACLE at large forget setStructGuard vs ORACLE · CIFAR-100 (k=256)Atest accuracy: 65.31 -> 56.91Hurt

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