AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Act Like a Radiologist: Towards Reliable Multi-View Correspondence Reasoning for Mammogram Mass Detection

Yuhang Liu, Fandong Zhang, Chaoqi Chen, Siwen Wang, Yizhou Wang, Yizhou Yu

TPAMI 2021 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 55 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 pseudo landmarks instead of uniform grids (ablation)AG-RCNN · DDSMR@0.5 recall: 77.7 -> 82.0Improved
increase pseudo landmark nodes from PL(1, 1) to PL(66, 71) (ablation)AG-RCNN · DDSMR@0.5 recall: 77.0 -> 82.0Improved
increase pseudo landmark nodes from PL(1, 1) to PL(66, 71) (ablation)AG-RCNN · In-houseR@0.5 recall: 84.5 -> 87.6Improved
use bipartite graph node mapping instead of cropping a fixed region (ablation)AG-RCNN PL(66, 71) · DDSMR@0.5 recall: 78.4 -> 82.0Improved
use k=3 instead of k=1 with dense nodes (ablation)AG-RCNN PL(66, 71) · DDSMR@0.5 recall: 80.1 -> 82.0Improved
use larger k=3 with sparse nodes instead of k=2 (ablation)AG-RCNN PL(21, 25) · DDSMR@0.5 recall: 81.1 -> 80.1Hurt
add geometric edges H^g (ablation)Mask RCNN with bipartite graph · DDSMR@0.5 recall: 76.7 -> 77.7Improved
add semantic edges H^s (ablation)Mask RCNN with bipartite graph · DDSMR@0.5 recall: 76.7 -> 78.4Improved
combine H^g and H^s (ablation)Mask RCNN with bipartite graph · DDSMR@0.5 recall: 76.7 -> 79.5Improved
use multi-branch IGN(1, 3, 5) instead of IGN(1) (ablation)Inception graph network · DDSMR@0.5 recall: 78.0 -> 79.1Improved
add BGN (ablation)Mask RCNN · DDSMR@0.5 recall: 76.7 -> 79.5Improved
add IGN (ablation)Mask RCNN · DDSMR@0.5 recall: 76.7 -> 79.1Improved

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