atlas

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

Attributes for Improved Attributes: A Multi-Task Network Utilizing Implicit and Explicit Relationships for Facial Attribute Classification

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 154 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
share lower layers and group attributes in multi-task CNN (MCNN) vs independent CNNs (ablation)attribute CNN · CelebAaccuracy: 90.95 -> 91.37 (Heavy Makeup)Helped
multi-task MCNN vs independent CNNs (ablation)attribute CNN · LFWAaccuracy: 92.15 -> 91.22 (Eyeglasses)Mixed
add AUX score-level relationship network (ablation)MCNN · CelebAaccuracy: 86.82 -> 86.63 (Necklace); 91.37 -> 91.55 (Heavy Makeup)Mixed
multi-task MCNN instead of 40 independent CNNsattribute CNN · CelebAtraining time: 40 hours to 2.5 hoursHelped
independent CNNs without pretraining vs Liu et al.attribute CNN · CelebAaccuracy: 84 -> 96.07 (Blurry)Helped

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