AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learning Structural Similarity of User Interface Layouts using Graph Networks

Dipu Manandhar, Dan Ruta, John Collomosse

ECCV 2020 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 29 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 triplet supervision with IoU weak labels (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 48.3 -> 51.3Improved
add triplet supervision with IoU weak labels (ablation)GCN-CNN layout embedding · RICOMPixAcc@10 (%): 56.5 -> 61.0Improved
add containment feature (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 47.4 -> 48.0Improved
add directed graph connectivity (ablation)GCN-CNN layout embedding · RICOMPixAcc@10 (%): 57.0 -> 57.7Improved
add self-attention readout pooling (ablation)GCN-CNN layout embedding · RICOMPixAcc@10 (%): 57.7 -> 58.0Improved
add triplet supervision at the end of cumulative stack (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 48.3 -> 51.3Improved
use strided convolution instead of upsampling in decoder (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 47.1 -> 48.3Improved
use directed instead of undirected graph, triplet trained (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 51.0 -> 51.3Improved
add containment feature with triplet supervision (ablation)GCN-CNN layout embedding · RICOMIoU@5 (%): 53.4 -> 54.1Improved
add containment feature (ablation)GCN-CNN layout embedding · RICOMIoU@1 (%): 61.9 -> 60.0Hurt
use self-attention readout instead of average pooling (512-D, unsupervised) (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 47.4 -> 47.1No clear effect
use self-attention readout instead of average/inverse pooling (2048-D, TRI) (ablation)GCN-CNN layout embedding · RICOMIoU@10 (%): 51.1 -> 51.3No 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