AI Paper Atlas

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

CP-mtML: Coupled Projection Multi-Task Metric Learning for Large Scale Face Retrieval

Binod Bhattarai, Gaurav Sharma, Frederic Jurie

CVPR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 9 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 age-matching auxiliary task using coupled projectionsidentity retrieval with LBP features · LFW, no distractors, K=21-call@K: 38.1 -> 46.1Improved
add an expression-matching auxiliary task using coupled projectionsidentity retrieval with LBP features · LFW, 1M distractors, K=51-call@K: 37.4 -> 43.3Improved
add an expression-matching auxiliary task using coupled projectionsidentity retrieval with CNN features · LFW, no distractors, K=51-call@K: 85.1 -> 86.5Improved
combine the common projection with the identity-task projection (ablation)CP-mtML identity retrieval · LFW, LBP, K=201-call@K: 51.8 -> 69.5Improved
add the identity-task projection to the common projection (ablation)CP-mtML identity retrieval · LFW, LBP, K=201-call@K: 64.8 -> 69.5Improved
use only the auxiliary-task projection instead of the combined projections (ablation)CP-mtML identity retrieval · LFW, LBP, K=201-call@K: 69.5 -> 13.0Hurt
increase projection dimension from d=32 to d=64 (ablation)CP-mtML (expr), identity retrieval with LBP · LFW, 1M distractors1-call@10: +13.5Improved
increase projection dimension from d=64 to d=128 (ablation)CP-mtML (expr), identity retrieval with LBP · LFW, 1M distractors1-call@10: +3.5Improved
increase projection dimension from d=32 to d=64 (ablation)CP-mtML (expr), identity retrieval with CNN · LFW, 1M distractors1-call@10: +1.9Improved
increase projection dimension from d=64 to d=128 (ablation)CP-mtML (expr), identity retrieval with CNN · LFW, 1M distractors1-call@10: -2.1Hurt
use a single metric trained on the union of identity and auxiliary-task pairs instead of task-coupled projectionsidentity retrieval with LBP · LFW, no distractors, K=21-call@K: 46.1 -> 21.7Hurt
use identity-matching auxiliary data with coupled projectionsage retrieval with CNN features · MORPH age retrieval1-call@KHurt

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