TabSOM: A tabular-to-image encoding method based on self-organizing maps

• URL: http://arxiv.org/abs/2608.13513v1
• Date: Thu, 13 Aug 2026 17:35:37 GMT
• Title: TabSOM: A tabular-to-image encoding method based on self-organizing maps
• Abstract summary: Tabular-to-image methods are novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers.<n>We propose TabSOM, a spatial-to-image encoding built on the Self-Organizing Map (SOM)<n>Two SOM-derived interpretability approaches are introduced: a prototype-inspired partial dependence plot and a class-separation importance score.
• Score: 0.9954435559869313
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixel location derived from a dimensionality-reduction method (e.g., t-SNE, UMAP, PCA). However, they encode only the marginal value of each feature and discard information about feature relationships. We propose TabSOM, a tabular-to-image encoding built on the Self-Organizing Map (SOM), which provides: (i) a spatial layout in which every input feature occupies a fixed canvas position derived from its component plane via collision-free Hungarian assignment; and (ii) a graph that captures pairwise feature relationships derived from the SOM component planes. The resulting image stacks two multi-scale node channels: one encodes feature values at fixed scales, while the other encodes pairwise feature interactions as spatial connections between related features. Two SOM-derived interpretability approaches are introduced: a prototype-inspired partial dependence plot and a class--separation importance score. Benchmarked against twelve existing tabular-to-image methods across public binary-classification datasets, TabSOM ranks first or second on every dataset and achieves the lowest variance of any method evaluated. Interpretability obtained with TabSOM was validated against Random Forest, XGBoost, and SHAP, the class-separation score shows reasonable agreement with established baselines on the top-ranked features while capturing complementary structural information from input data. These results demonstrate that TabSOM provides an effective and interpretable approach for applying deep learning architectures to tabular data, bridging the performance--interpretability gap in this domain.

Related papers

• Test-Time Augmentation for Tabular-to-Image Classifiers under Distribution Shifts [2.1272291601429116]
  Test-Time Augmentation (TTA) is an effective approach in image classification to improve model robustness.<n>This work evaluates the impact of TTA techniques on predictive performance under Out-Of-Distribution (OOD) for representations generated by tabular-to-image methods.<n>The results indicate that TTA improves OOD performance, with composite and photometric strategies providing the best trade-off between robustness and variance.
  arXiv  Detail & Related papers  (2026-08-04T12:26:58Z)
• LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models [56.999481798138625]
  LimiX-2M is a 2M- parameter model that outperforms larger TabPFN-v2 and TabICL baselines on widely used benchmarks.<n>We present a unified tokenize-and-route framework for strong Tabular foundation models (TFMs)<n>Results highlight value-aware tokenization and readout-aligned routing as key levers for improving the accuracy--efficiency trade-off in TFMs.
  arXiv  Detail & Related papers  (2026-06-03T06:07:33Z)
• H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers [2.7415651415305597]
  We introduce H-Sets, a novel framework for discovering and attributing higher-order feature interactions in image classifiers.<n>We attribute each set with IDG-Vis, a set-level extension of Integrated Directional Gradients that integrates directional gradients along pixel-space paths.<n> Evaluations across VGG, ResNet, DenseNet and MobileNet models on ImageNet and CUB datasets show that H-Sets generate more interpretable and faithful saliency maps.
  arXiv  Detail & Related papers  (2026-04-23T20:03:17Z)
• Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning [3.884856136722027]
  We introduce Orion-MSP, a new ICL architecture featuring multi-scale processing, block-sparse attention, and Perceiver-style memory.<n>Orion-MSP matches or surpasses state-of-the-art performance while scaling effectively to high-dimensional tables.
  arXiv  Detail & Related papers  (2025-11-04T18:43:44Z)
• Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds [49.95082206008502]
  Alignment across Trees is a method that constructs and aligns tree-like hierarchical features for both image and text modalities.<n>We introduce a semantic-aware visual feature extraction framework that applies a cross-attention mechanism to visual class tokens from intermediate Transformer layers.
  arXiv  Detail & Related papers  (2025-10-31T11:32:15Z)
• Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation [120.23172120151821]
  We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models.<n>We introduce an automated pipeline that constructs image pairs with annotated semantic and visual correspondences.<n>We propose a new metric, Visual Semantic Matching, that quantifies visual inconsistencies in subject-driven image generation.
  arXiv  Detail & Related papers  (2025-09-26T07:11:55Z)
• TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization [2.1067477213933503]
  TabGLM (Tabular Graph Language Model) is a novel multi-modal architecture designed to model both structural and semantic information from a table.<n>It transforms each row of a table into a fully connected graph and serialized text, which are encoded using a graph neural network (GNN) and a text encoder, respectively.<n> Evaluations across 25 benchmark datasets demonstrate substantial performance gains.
  arXiv  Detail & Related papers  (2025-02-26T05:32:45Z)
• Table2Image: Interpretable Tabular Data Classification with Realistic Image Transformations [5.62508658491325]
  This paper introduces Table2Image, a novel framework that transforms tabular data into realistic and diverse image representations.<n>We also present an interpretability framework that integrates insights from both the original data and its transformed image representations.
  arXiv  Detail & Related papers  (2024-12-09T07:24:31Z)
• PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer [51.260384040953326]
  Handwritten Mathematical Expression Recognition (HMER) has wide applications in human-machine interaction scenarios. We propose a position forest transformer (PosFormer) for HMER, which jointly optimize two tasks: expression recognition and position recognition. PosFormer consistently outperforms the state-of-the-art methods 2.03%/1.22%/2, 1.83%, and 4.62% gains on datasets.
  arXiv  Detail & Related papers  (2024-07-10T15:42:58Z)
• A Closer Look at Deep Learning Methods on Tabular Datasets [78.61845513154502]
  We present an extensive study on TALENT, a collection of 300+ datasets spanning broad ranges of size.<n>Our evaluation shows that ensembling benefits both tree-based and neural approaches.
  arXiv  Detail & Related papers  (2024-07-01T04:24:07Z)
• Dual Attention GANs for Semantic Image Synthesis [101.36015877815537]
  We propose a novel Dual Attention GAN (DAGAN) to synthesize photo-realistic and semantically-consistent images. We also propose two novel modules, i.e., position-wise Spatial Attention Module (SAM) and scale-wise Channel Attention Module (CAM) DAGAN achieves remarkably better results than state-of-the-art methods, while using fewer model parameters.
  arXiv  Detail & Related papers  (2020-08-29T17:49:01Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.