AI Paper Atlas

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

Joint Acne Image Grading and Counting via Label Distribution Learning

Xiaoping Wu, Ni Wen, Jie Liang, Yu-Kun Lai, Dongyu She, Ming-Ming Cheng, Jufeng Yang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 114 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
use label distribution instead of single label for grading (ablation)ResNet-50 grading · ACNE04accuracy: 78.42 -> 79.31Improved
use label distribution of lesion number instead of single label for counting (ablation)ResNet-50 counting · ACNE04MAE: 4.16 -> 3.24Improved
use lesion-count label distribution, with counts converted to grade (ablation)ResNet-50 counting · ACNE04accuracy: 75.69 -> 81.09Improved
use dynamically generated grading label distribution instead of standard LDL (ablation)ResNet-50 grading · ACNE04accuracy: 79.31 -> 82.05Improved
add joint grading and counting multi-task learning (ablation)Ours(G) · ACNE04accuracy: 82.05 -> 82.53Improved
add joint grading and counting multi-task learning (ablation)LDL(C) · ACNE04MAE: 3.24 -> 3.01Improved
add Lcnt2cls loss and averaging of grading and counting predictions (ablation)Ours(G+C) · ACNE04accuracy: 82.53 -> 84.11Improved
add Lcnt2cls loss and averaging of grading and counting predictions (ablation)Ours(G+C) · ACNE04MAE: 3.01 -> 2.93Improved
increase lambda from 0.1 up to 0.6 (ablation)Ours · ACNE04accuracy and MAEMixed
replace ResNet-50 with the proposed methodResNet-50 · ACNE04accuracy: 78.42 -> 84.11Improved
use proposed method instead of Faster R-CNN based countingF-RCNN · ACNE04MAE: 6.70 -> 2.93Improved
use deep features instead of hand-crafted featuresSVM classifiers · ACNE04accuracy: 48.22 -> 78.42Improved

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