AI Paper Atlas

Research map / Detection and segmentation / CNN features

Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection

Junjia Huang, Haofeng Li, Xiang Wan, Guanbin Li

ICCV 2023 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 19 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 Adaptive Affine Transformer for local views and EMA global branch (ablation)single-branch baseline · Lizardmean classification F-score: 0.447 -> 0.525Improved
replace random crop/rotation/affine with learned AAT (with global loss) (ablation)AC-Former · Lizardmean classification F-score: 0.526/0.502/0.532 -> 0.557Improved
add global-branch supervised loss (ablation)BL+AAT · Lizardmean classification F-score: 0.525 -> 0.557Improved
add random crop augmentation to baseline (ablation)single-branch baseline · Lizardmean classification F-score: 0.447 -> 0.445No clear effect
increase number of warped images from 4 to 5 (ablation)AC-Former · LizardF-scoreHurt
use AC-Former instead of MCSpatNet on Lizardnuclei detection · Lizardmean classification F-score: 0.349 -> 0.557Improved
train with dual-branch AAT design (training only)AC-Former · CoNSePinference time: 0.097 -> 0.097No clear effect

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