AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Structured Landmark Detection via Topology-Adapting Deep Graph Learning

Weijian Li, Yuhang Lu, Kang Zheng, Haofu Liao, Chihung Lin, Jiebo Luo, Chi-Tung Cheng, Jing Xiao, Le Lu, Chang-Fu Kuo, Shun Miao

ECCV 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 110 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 learned graph connectivity instead of uniform (with shape feature) (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.12 -> 3.04Improved
add information exchange (uniform connectivity) instead of self-connectivity only (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.31 -> 3.16Improved
add shape feature to graph signal with self connectivity (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.31 -> 3.16Improved
add shape feature to graph signal with learned connectivity (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.08 -> 3.04Improved
use perspective instead of affine transformation in GCN-global (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.13 -> 3.04Improved
use GCN-global instead of a CNN block (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.12 -> 3.04Improved
use GCN-local instead of an MLP block (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.18 -> 3.04Improved
increase GCN-local steps from 1 to 3 (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.24 -> 3.04Improved
increase GCN-local steps from 3 to 7 (ablation)DAG HRNet18 · 300W Full set (inter-ocular)NME (%): 3.04 -> 3.11Hurt
use DAG graph regression instead of local feature regression (ablation)HRNet18 · 300W Full set (inter-ocular)NME (%): 3.72 -> 3.04Improved
use DAG instead of global feature regression with VGG16 backbone (ablation)VGG16 · 300W Full set (inter-ocular)NME (%): 4.66 -> 3.66Improved
add WING loss to DAGDAG · 300W Full set (inter-pupil)NME (%): 4.27 -> 4.21Improved

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