AI Paper Atlas

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

SPL-Net: Spatial-Semantic Patch Learning Network for Facial Attribute Recognition with Limited Labeled Data

Yan Yan, Ying Shu, Si Chen, Jing‐Hao Xue, Chunhua Shen, Hanzi Wang

IJCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 8 citations (OpenAlex)

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

add all three auxiliary tasks (two-stage pretraining) to baseline · CelebA 0.02% labeled · accuracy (%): 76.34 -> 79.33 Improved

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 all three auxiliary tasks (two-stage pretraining) to baseline (ablation)baseline PreAct ResNet-18 · CelebA 0.02% labeledaccuracy (%): 76.34 -> 79.33Improved
add all three auxiliary tasks to baseline (ablation)baseline · LFWA 0.5% labeledaccuracy (%): 4.51% improvementImproved
add all three auxiliary tasks to baseline (ablation)baseline · MAAD 0.02% labeledaccuracy (%): 63.04 -> 69.01Improved
add multi-branch shared subnetwork (MSS) to baseline (ablation)baseline · CelebA/LFWA/MAAD low labelaccuracy (%): 0.58% on CelebA, 0.98% on LFWA, 0.57% on MAADImproved
keep whole region branch rather than feature fusion block (ablation)SPL-Net · CelebA 0.02% labeledaccuracy (%): 78.21 -> 79.33Improved
add spatial mutual exclusion (SME) loss (ablation)SPL-Net · CelebA 0.02% labeledaccuracy (%): 78.83 -> 79.33Improved
add adversarial training in MSS (ablation)SPL-Net · CelebA 0.02% labeledaccuracy (%): 78.89 -> 79.33Improved
use adversarial training instead of L2 contrastive loss (ablation)SPL-Net · CelebA 0.02% labeledaccuracy (%): 78.01 -> 79.33Improved
use two-stage learning instead of one-stage semi-supervised (ablation)SPL-Net · CelebA 0.02% labeledaccuracy (%): 75.23 -> 79.33Improved
use SE-based DCA attention instead of CBAM blocks (ablation)SPL-Net · CelebA 0.02% labeledaccuracy (%): 79.03 -> 79.33Improved
add patch classification task to PRT+PST (ablation)SPL RS · CelebA/LFWA/MAAD low labelaccuracy (%): 0.37%, 1.15%, 0.62%Improved
add patch segmentation task to PRT+PCT (ablation)SPL RC · CelebA/LFWA/MAAD low labelaccuracy (%): 0.83%, 1.57%, 1.25%Improved

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