AI Paper Atlas

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

Adaptive Deep Disturbance-Disentangled Learning for Facial Expression Recognition

Delian Ruan, Rongyun Mo, Yan Yan, Si Chen, Jing‐Hao Xue, Hanzi Wang

IJCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 48 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 attention blocks (Se subnetwork) (ablation)Baseline · MMIaccuracy (%): 79.16 -> 81.22Improved
add multi-level attention mechanism (ablation)Baseline at · MMIaccuracy (%): 81.22 -> 81.47Improved
add disturbance subnetwork Sd (gender) (ablation)Baseline mat · MMIaccuracy (%): 81.47 -> 82.88Improved
add pose to the disturbing factors of Sd (ablation)DDL gar&id&il · MMIaccuracy (%): 84.25 -> 83.56Hurt
add adaptive disturbance feature learning (ADFL) (ablation)DDL gar&id&il&p · MMIaccuracy (%): 1.84% and 0.91% improvements (MMI, RAF-DB)Improved
add mutual information neural estimator (MINE) (ablation)DDL gar&id&il&p · MMIaccuracy (%): 83.56 -> 85.56Improved
combine ADFL and MINE (ablation)DDL gar&id&il&p · MMIaccuracy (%): 2.57% and 1.17% (MMI, RAF-DB)Improved
add DFEM prior knowledge for the disturbance subnetwork (ablation)ADDL · MMIaccuracy (%): 83.13 -> 86.13Improved
train DFEM on Multi-PIE and RAF-DB instead of Multi-PIE only (ablation)ADDL · MMIaccuracy (%): 85.00 -> 86.13Improved
pretrain backbone on MS-Celeb-1M instead of no pretraining (ablation)ADDL · MMIaccuracy (%): 70.76 -> 86.13Improved
pretrain backbone on MS-Celeb-1M instead of ImageNet (ablation)ADDL · RAF-DBaccuracy (%): 87.58 -> 89.34Improved
enable adversarial training (lambda1 0.0 to 1.0) (ablation)ADDL · MMIaccuracy (%): 83.39 -> 86.13Improved

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