AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Interpretable Structure-Evolving LSTM

Xiaodan Liang, Liang Lin, Xiaohui Shen, Jiashi Feng, Shuicheng Yan, Eric P. Xing

CVPR 2017 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 94 citations (OpenAlex)

Check 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
Learn adaptive multi-level graph structures instead of using the fixed Graph LSTM graphStructure-evolving LSTM · PASCAL-Person-PartAverage IoU: 60.16 -> 63.57Improved
Use stochastic graph merging instead of deterministic merging at threshold 0.7 (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 62.20 -> 63.57Improved
Use deterministic merging at threshold 0.5 (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 59.63Hurt
Use deterministic merging at threshold 0.9 (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 60.99Hurt
Use predefined multi-scale superpixel maps instead of adaptively evolved graph structures (ablation)Graph LSTM · PASCAL-Person-PartAverage IoU: 61.02 -> 63.57Hurt
Increase the structure-evolving LSTM depth from 1 to 5 layers (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 58.19 -> 63.57Improved
Use only the 1st-level graph prediction instead of combining predictions across levels (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 57.19Hurt
Use only the 2nd-level graph prediction instead of combining predictions across levels (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 61.29Hurt
Use only the 3rd-level graph prediction instead of combining predictions across levels (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 60.13Hurt
Use only the 4th-level graph prediction instead of combining predictions across levels (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 59.87Hurt
Use only the 5th-level graph prediction instead of combining predictions across levels (ablation)Structure-evolving LSTM · PASCAL-Person-PartAverage IoU: 63.57 -> 59.23Hurt
Learn hierarchical graph structures instead of using the fixed Graph LSTM graphStructure-evolving LSTM · Horse-Cow (Horse)IOU: 74.75 -> 76.87Improved

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