AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Hallucinating Visual Instances in Total Absentia

Jiayan Qiu, Yiding Yang, Xinchao Wang, Dacheng Tao

ECCV 2020 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 20 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 global autoencoder feature (ablation)GCN module · COCOaccuracy (%): 86.55 -> 87.93Improved
add global autoencoder feature (ablation)GNN baseline · COCOaccuracy (%): 75.67 -> 79.23Improved
add global autoencoder feature (ablation)GCN module · COCObalanced accuracy (%): 84.19 -> 85.62Improved
add spatial coordinates to node features (ablation)GCN module · COCOaccuracy (%): 84.86 -> 87.93Improved
add spatial coordinates to node features (ablation)GNN baseline · COCOaccuracy (%): 77.64 -> 79.23Improved
use cross-entropy instead of KL divergence loss (ablation)GCN module · COCOaccuracy (%): 85.46 -> 87.93Improved
use cross-entropy instead of KL divergence loss (ablation)GNN baseline · COCOaccuracy (%): 73.01 -> 79.23Improved
use attention-based GCN instead of Kipf GNN (ablation)class prediction · COCOaccuracy (%): 79.23 -> 87.93Improved
train OGAN jointly with GRAN end-to-end (ablation)object generator · GAN pre-trainingPSNR: 26.23 -> 27.14Improved
train refinement network jointly end-to-end (ablation)refinement network · GAN pre-trainingPSNR: 29.06 -> 29.17Improved
train OGAN jointly with GRAN end-to-end (ablation)object generator · GAN pre-trainingSSIM: 0.9002 -> 0.9078Improved
train GCN and GAN modules end-to-end rather than separately (ablation)full framework · COCOvisual plausibilityImproved

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