AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View

Jianan Fan, Dongnan Liu, Canran Li, Hang Chang, Heng Huang, Filip Braet, Mei Chen, Weidong Cai

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 5 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 tissue correspondence discovery (TCD) masking-restoration task (ablation)Mask R-CNN source-only baseline · Breast->TestisF score: 0.409 -> 0.446Improved
add self-adaptive dynamic distillation weights (SA) (ablation)TCD + NCD + MD · Breast->TestisF score: 0.557 -> 0.589Improved
add nuclear cluster correspondence discovery (NCD) (ablation)TCD · Breast->TestisF score: 0.446 -> 0.472Improved
add NCD to TCD for segmentation (ablation)TCD · Breast->ThyroidPQ: 0.189 -> 0.180Hurt
add NCD to TCD for segmentation (ablation)TCD · Breast->Bile-ductPQ: 0.227 -> 0.214Hurt
add TCD (image-level nuclei masking and restoration) (ablation)Mask R-CNN source-only baseline · Breast->TestisPQ: 0.222 -> 0.232Improved
reduce SDD loss weight lambda3 below 1.0 (ablation)Full method · Breast->TestisF score and PQHurt
increase NCD loss weight lambda2 (ablation)Full method · Breast->TestisPQHurt
avoid category pseudo-labels (surrogate tasks instead of self-training)Cross-domain nuclei recognition · Breast->TestisF scoreImproved
proposed method versus best UDA baselineCross-domain nuclei recognition · Breast->TestisF score (class average): 0.514 -> 0.589Improved

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