AI Paper Atlas

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

Robust RGB-D Face Recognition Using Attribute-Aware Loss

Luo Jiang, Juyong Zhang, Bailin Deng

TPAMI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 56 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 attribute-aware loss to softmax (ablation)softmax, RGB input · Private RGB-D, train set 1Rank-1 identification rate (%): 83.12 -> 92.24Improved
add attribute-aware loss to softmax + center (ablation)center loss model, depth input · Private RGB-D, train set 1Rank-1 identification rate (%): 88.49 -> 93.29Improved
add attribute-aware loss to softmax + center (ablation)center loss model, RGB input · Private RGB-D, train set 1Rank-1 identification rate (%): 96.56 -> 96.78Improved
add depth to RGB input (six-channel) (ablation)softmax · Private RGB-D, train set 1Rank-1 identification rate (%): 83.12 -> 88.93Improved
train on unbalanced instead of balanced set (ablation)softmax · Private RGB-D, RGB+DepthRank-1 identification rate (%): 88.93 -> 86.59Hurt
train on unbalanced instead of balanced set (ablation)softmax + attribute-aware · Private RGB-D, RGB+DepthRank-1 identification rate (%): 96.26 -> 96.16No clear effect
use detected attribute features instead of ground-truth attributes (ablation)softmax + attribute-aware · Private RGB-D, set 1, RGB+DepthRank-1 identification rate (%): 96.26 -> 92.84Hurt
drop age attribute (use gender + ethnicity) (ablation)softmax + attribute-aware · Private RGB-D, set 1, RGB+DepthRank-1 identification rate (%): 96.26 -> 94.16Hurt
feature-level fusion at middle instead of signal-level fusion (ablation)softmax · Private RGB-D, set 1Rank-1 identification rate (%): 88.93 -> 89.44Improved
feature-level fusion at back instead of signal-level fusion (ablation)softmax · Private RGB-D, set 1Rank-1 identification rate (%): 88.93 -> 82.67Hurt
add attribute-aware loss to softmax (ablation)softmax, yaw -90 · Small RGB-D pose setRank-1 identification rate (%): 62.65 -> 81.15Improved
add attribute-aware loss to softmax (ablation)softmax, yaw +90 · Small RGB-D pose setRank-1 identification rate (%): 50.12 -> 65.88Improved

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