AI Paper Atlas

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

Learning Deep Representation for Face Alignment with Auxiliary Attributes

Zhanpeng Zhang, Ping Luo, Chen Change Loy, Xiaoou Tang

TPAMI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 427 citations (OpenAlex)

This paper tried a common change: Add a reconstruction / auxiliary loss

add a random-objective auxiliary task · MAFL · mean error No clear effect

What 987 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 dynamic task coefficient instead of task-wise early stopping (no correlation learning) (ablation)TCDCN · MAFLmean error (x10^-2): 8.35 -> 8.07Improved
add dynamic task coefficient instead of task-wise early stopping (with correlation learning) (ablation)TCDCN · MAFLmean error (x10^-2): 8.21 -> 7.95Improved
add inter-task correlation learning with dynamic task coefficient (ablation)TCDCN · MAFLmean error (x10^-2): 8.07 -> 7.95Improved
add inter-task correlation learning with task-wise early stopping (ablation)TCDCN · MAFLmean error (x10^-2): 8.35 -> 8.21Improved
add dynamic task coefficient to training (ablation)TCDCN · MAFLtraining convergenceImproved
add all auxiliary attribute tasks (FLD+all) to landmark detection only (ablation)TCDCN · MAFLfailure rate: over 7%Improved
add head pose and global attribute groups as auxiliary tasks (ablation)TCDCN · MAFLmean errorImproved
add eyes or mouth attribute groups as auxiliary tasks (ablation)TCDCN · MAFLmean errorImproved
add a random-objective auxiliary task (ablation)TCDCN · MAFLmean errorNo clear effect
use TCDCN instead of CFSSTCDCN · Helen (194 landmarks)mean error (%): 4.74 -> 4.63Improved
use TCDCN instead of CFSSTCDCN · 300-W challenging subsetmean error (%): 9.98 -> 8.60Improved
use TCDCN instead of CFSSTCDCN · 300-W common subsetmean error (%): 4.73 -> 4.80Hurt

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