AI Paper Atlas

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

From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal

Daniel George, Charles Yeh, Daniel Lee, Yifei Zhang

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 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
Apply ISP projectionCLIP · CelebA-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 19.8% -> 13.0%Improved
Apply ISP projectionCLIP · VGGFace2-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 14.1% -> 2.3%Improved
Apply ISP projectionDINOv3 · CelebA-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 6.8% -> 2.8%Improved
Apply ISP projectionSSCD · VGGFace2-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 4.5% -> 0.5%Improved
Apply ISP projectionDINOv2 · VGGFace2-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 1.6% -> 1.5%No clear effect
Fit ISP on the other dataset (cross-dataset transfer)CLIP · CelebA-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 19.8% -> 10.2%Improved
Fit ISP on the other dataset (cross-dataset transfer)DINOv2 · VGGFace2-20 (k=16)Ridge open-set TAR@FAR=1e-4 (%): 1.6% -> 2.7%Mixed
Apply ISP projectionDINOv2, DINOv3, CLIP · ImageNet k-NNTop-1 accuracy, normalized: 100.1%, 97.3%, 98.3% of rawNo clear effect
Apply ISP projectionSSCD · ImageNet k-NNTop-1 accuracy, normalized: 85.4% of rawHurt
Use ISP instead of LEACEDINOv3 · ImageNet k-NNTop-1 accuracy, normalized: 97.3% vs 97.4%No clear effect
Apply ISP projectionNon-FR encoders · Template inversionVerification rateNo clear effect
Apply ISP projectionNon-FR encoders · Non-linear MLP probeTARImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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