AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer

Liang Lin, Yiming Gao, Ke Gong, Meng Wang, Xiaodan Liang

TPAMI 2020 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 21 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 Intra-Graph Reasoning with adjacency matrix to basic network (ablation)DeepLab v3+ · PASCAL-Person-Partmean IoU (%): 67.84 -> 68.34Improved
add adjacency matrix A^e prior to Intra-Graph Reasoning (ablation)Intra-Graph Reasoning · PASCAL-Person-Partmean IoU (%): 67.89 -> 68.34Improved
add Inter-Graph Transfer via handcraft relation (ablation)Graphonomy with CIHP pre-training · PASCAL-Person-Partmean IoU (%): 70.47 -> 70.22Hurt
use feature similarity for Inter-Graph Transfer (ablation)Graphonomy with CIHP pre-training · PASCAL-Person-Partmean IoU (%): 70.47 -> 71.05Improved
use learnable matrix for Inter-Graph Transfer (ablation)Graphonomy with CIHP pre-training · PASCAL-Person-Partmean IoU (%): 70.47 -> 70.94Improved
combine feature and semantic similarity transfer (ablation)Graphonomy · PASCAL-Person-Partmean IoU (%): 71.05 -> 71.14Improved
add learnable matrix and handcraft relation to the combination (ablation)Graphonomy · PASCAL-Person-Partmean IoU (%): 71.14 -> 70.69Hurt
replace fine-tuning with Inter-Graph Transfer, 100% data (ablation)Graphonomy (CIHP) · PASCAL-Person-Partmean IoU (%): 70.33 -> 71.14Improved
replace fine-tuning with Inter-Graph Transfer, 50% data (ablation)Graphonomy (CIHP) · PASCAL-Person-Partmean IoU (%): 68.45 -> 70.03Improved
increase Intra-Graph layers from 1 to 3 (ablation)Intra-Graph Reasoning · PASCAL-Person-Partmean IoU (%): 67.80 -> 68.34Improved
increase Intra-Graph layers from 3 to 5 (ablation)Intra-Graph Reasoning · PASCAL-Person-Partmean IoU (%): 68.34 -> 68.36No clear effect
train one universal model over all datasets instead of a dataset-specific transferGraphonomy · PASCAL-Person-Partmean IoU (%): 71.14 -> 70.99Hurt

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