AI Paper Atlas

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

R-ESC: Robustly Erasing Space Concepts via Stochastic Feature Remapping

Kang Eun Jeon, Yunsung Kang, Do Kang, Tae-Young Lee, Gyeong-Moon Park, Jong Hwan Ko

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 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 prototype-orthogonal projection to remapping (ablation)Remap · CIFAR-10 (KR setting, lr 0.1)HM: 0.27 -> 66.89Improved
add prototype-orthogonal projection to remapping (ablation)Remap · CIFAR-10 (class erasure)HM: 94.47 -> 99.94Improved
add prototype-orthogonal projection to erasure (ablation)Erase · CIFAR-10 (class erasure)D_f: 14.38 -> 0.00Improved
add prototype-orthogonal projection to erasure (ablation)Erase · CIFAR-10 (KR setting, lr 0.1)HM: 1.94 -> 1.97No clear effect
replace erasure with remapping (with PO) (ablation)Erase · CIFAR-10 (KR setting, lr 0.1)HM: 1.97 -> 66.89Improved
replace single-expert remapping with multi-expert stochastic remapping (ablation)Remap · CIFAR-10 (KR setting, lr 0.1)HM: 66.89 -> 92.37Improved
replace single-expert remapping with multi-expert stochastic remapping (ablation)Remap · CIFAR-100 (KR setting, lr 0.1)HM: 62.76 -> 99.89Improved
replace single-expert remapping with multi-expert stochastic remapping (ablation)Remap · Tiny-ImageNet (KR setting, lr 0.1)HM: 59.60 -> 97.99Improved
remap forget class 4 to class 2 instead of class 0 (ablation)Remap · CIFAR-10 (KR setting, lr 0.1)HM: 66.89 -> 34.06Hurt
use trained conditional router with load balancing (P-T-B) (ablation)R-ESC · CIFAR-10 (KR setting, N=8, lr 0.1)HM_t: 85.24 -> 91.79Improved
use trained conditional router with load balancing (P-T-B) (ablation)R-ESC · CIFAR-100 (KR setting, N=80, lr 0.1)HM: 99.97 -> 97.34Hurt
apply remapping instead of erasure at third-last layer (ablation)Erase · CIFAR-10 (third-last layer)HM: 69.40 -> 84.76Improved

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