AI Paper Atlas

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

Pairwise Linear Regression Classification for Image Set Retrieval

Qingxiang Feng, Yicong Zhou, Rushi Lan

CVPR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 56 citations (OpenAlex)

Check 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 an unrelated-subspace metric and combine it with the related metric (PLRC-I)DLRC · LFW, 10 × 10recognition rate: 91.94 -> 95.16Improved
Use PLRC-I instead of DLRCimage-set recognition · LFW, 15 × 10recognition rate: 95.16 -> 96.77Improved
Use PLRC-I instead of DLRCimage-set recognition · ARrecognition rate: 96.00 -> 97.33Improved
Use PLRC-II instead of DLRCimage-set recognition · ARrecognition rate: 96.00 -> 95.00Hurt
Use PLRC-I instead of DLRCimage-set recognition · Honda/UCSDrecognition rate: 87.18 -> 89.74Improved
Use PLRC-II instead of DLRCimage-set recognition · Honda/UCSDrecognition rate: 87.18 -> 87.18No clear effect
Use PLRC-I instead of DLRCimage-set recognition · CMU Moborecognition rate: 93.06+3.4 -> 93.74+4.3Improved
Use PLRC-II instead of DLRCimage-set recognition · CMU Moborecognition rate: 93.06+3.4 -> 93.75+4.3Improved
Use PLRC-I instead of DLRCimage-set recognition · Caltech101, Scheme 1recognition rate: 70.20 -> 72.75Improved
Use PLRC-II instead of DLRCimage-set recognition · Caltech101, Scheme 1recognition rate: 70.20 -> 72.35Improved
Use PLRC-I instead of DLRCimage-set recognition · Caltech101, Scheme 2recognition rate: 80.39 -> 83.09Improved
Use PLRC-II instead of DLRCimage-set recognition · Caltech101, Scheme 2recognition rate: 80.39 -> 80.64No clear effect

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