Research map / Vision-language and multimodal / Cross-modal learning
iSyncTab: Learning Cross-Modal Feature Sequencing for Image-Tabular Data via Neural Synchrony
Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali, Gianfranco Doretto, Donald Adjeroh
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add memory tokens (ablation) | iSyncTab · DVM (w/ tuning) | accuracy: 87.60 -> 99.60 | Improved |
| add memory tokens (ablation) | iSyncTab · HAM (w/ tuning) | accuracy: 80.12 -> 86.82 | Improved |
| add memory tokens (ablation) | iSyncTab · HAM (w/o tuning) | accuracy: 77.90 -> 78.72 | Improved |
| add NS-PFS feature sequencing (ablation) | iSyncTab · DVM (w/o tuning) | accuracy: 96.80 -> 99.80 | Improved |
| add NS-PFS feature sequencing (ablation) | iSyncTab · HAM (w/ tuning) | accuracy: 78.60 -> 86.82 | Improved |
| add NS-PFS feature sequencing (ablation) | iSyncTab · HAM (w/o tuning) | accuracy: 78.16 -> 78.72 | Improved |
| use meaningful feature ordering instead of random column shuffle (ablation) | iSyncTab · DVM (w/o tuning) | accuracy: 86.72 -> 99.80 | Improved |
| use meaningful feature ordering instead of random column shuffle (ablation) | iSyncTab · HAM (w/o tuning) | accuracy: 62.06 -> 78.72 | Improved |
| add auxiliary sequencing loss (ablation) | iSyncTab · HAM (w/ tuning) | accuracy: 84.36 -> 86.82 | Improved |
| add auxiliary sequencing loss (ablation) | iSyncTab · DVM (w/ tuning) | accuracy: 98.70 -> 99.60 | Improved |
| use ResNet-50 instead of ResNeXt-50 backbone (ablation) | iSyncTab · HAM (w/ tuning) | accuracy: 84.28 -> 86.82 | Improved |
| use NS-PFS + OMT instead of concatenation fusion (ablation) | iSyncTab · HAM (w/ tuning) | accuracy: 78.42 -> 86.82 | Improved |
Closest papers by meaning
- Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images (ICML 2024 · similarity 0.85)
- SwitchTab: Switched Autoencoders Are Effective Tabular Learners (AAAI 2024 · similarity 0.85)
- STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification (CVPR 2025 · similarity 0.85)
- MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image (NeurIPS 2026 · similarity 0.85)
- TabM: Advancing tabular deep learning with parameter-efficient ensembling (ICLR 2025 · similarity 0.85)
- TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments (ICML 2025 · similarity 0.85)
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.
