AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images

Ramin Nakhli, Puria Azadi Moghadam, Haoyang Mi, Hossein Farahani, Alexander Baras, Blake Gilks, Ali Bashashati

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 31 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
Use AMIGO instead of the strongest listed baselinesurvival prediction · InUITC-Index: 0.55 ± 0.004 -> 0.57 ± 0.002Improved
Use AMIGO instead of the strongest listed baselinesurvival prediction · MIBCC-Index: 0.59 ± 0.007 -> 0.61 ± 0.004Improved
Add instance normalization after instance attention (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.53 ± 0.001 -> 0.57 ± 0.002; MIBC: 0.54 ± 0.005 -> 0.61 ± 0.004Improved
Share low-level modality branch weights while retaining modality-specific processing (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.56 ± 0.001 -> 0.57 ± 0.002; MIBC: 0.54 ± 0.016 -> 0.61 ± 0.004Improved
Keep modality branch weights partly shared rather than fully shared (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.53 ± 0.001 -> 0.57 ± 0.002; MIBC: 0.51 ± 0.005 -> 0.61 ± 0.004Improved
Use batch censored portion sampling (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.54 ± 0.001 -> 0.57 ± 0.002; MIBC: 0.58 ± 0.013 -> 0.61 ± 0.004Improved
Use shared instance attention rather than Transformer attention for within-modality aggregation (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.53 ± 0.002 -> 0.57 ± 0.002; MIBC: 0.55 ± 0.011 -> 0.61 ± 0.004Improved
Apply sparsity during training but not at inference (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.56 ± 0.001 -> 0.57 ± 0.002; MIBC: 0.55 ± 0.004 -> 0.61 ± 0.004Improved
Share instance attention across modalities (ablation)AMIGO · InUIT and MIBCC-Index: InUIT: 0.54 ± 0.001 -> 0.57 ± 0.002; MIBC: 0.58 ± 0.003 -> 0.61 ± 0.004Improved
Increase graph sparsity during trainingAMIGO · InUITFLOPs: from 3.5 to 0.7 GigaFlopsImproved
Train with sparse graph inputsAMIGO · InUITC-IndexNo 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