AI Paper Atlas

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

Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition

Xi Peng, Xiang Yu, Kihyuk Sohn, Dimitris N. Metaxas, Manmohan Chandraker

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 171 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 Siamese reconstruction regularization (ablation)MSMT · MultiPIE (P1, avg)rank-1 accuracy: 0.882 -> 0.905Improved
add Siamese reconstruction regularization (ablation)MSMT · 300WLP (avg)rank-1 accuracy: 0.971 -> 0.980Improved
replace direct L2 identity distance by reconstruction regularization (ablation)MSMT+L2 · MultiPIE (P1, avg)rank-1 accuracy: 0.900 -> 0.905Improved
add direct L2 distance between identity features of same subject (ablation)MSMT · MultiPIE (P1, avg)rank-1 accuracy: 0.882 -> 0.900Improved
add multi-source multi-task training instead of single-source fine-tuning (ablation)SS-FT · MultiPIE (P1, avg)rank-1 accuracy: 0.860 -> 0.882Improved
fine-tune on target dataset (ablation)SS · MultiPIE (P1, avg)rank-1 accuracy: 0.690 -> 0.860Improved
use N-pair loss instead of cross entropy (ablation)MSMT · MultiPIE (P1, avg)rank-1 accuracy: 0.882 -> 0.927Improved
add Siamese reconstruction on top of N-pair loss (ablation)MSMT-dagger · MultiPIE (P1, avg)rank-1 accuracy: 0.927 -> 0.929No clear effect
add Siamese reconstruction on top of N-pair loss (ablation)MSMT-dagger · 300WLP (avg)rank-1 accuracy: 0.977 -> 0.986Improved
add reconstruction regularization, cross-database train 300WLP test MultiPIEMSMT · MultiPIE (cross-database, P1 avg)rank-1 accuracy: 0.788 -> 0.808Improved
add reconstruction regularization, cross-database train MultiPIE test 300WLPMSMT · 300WLP (cross-database, avg)rank-1 accuracy: 0.904 -> 0.910Improved
add reconstruction regularization with P2 protocol (ablation)MSMT · MultiPIE (P2, avg)rank-1 accuracy: 0.939 -> 0.954Improved

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