# SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation

arXiv: https://arxiv.org/abs/2605.12389 · HTML: https://mlsanity.com/paper/2605.12389/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 52 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 17 of 17)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT](https://mlsanity.com/paper/2307.01984/) (2023)
- [Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation](https://mlsanity.com/paper/2102.04525/) (2021)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.10156/) (2024)
- [U-Net v2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2311.17791/) (2023)
- [Automated 3D Segmentation of Kidneys and Tumors in MICCAI KiTS 2023 Challenge](https://mlsanity.com/paper/2310.04110/) (2023)
- [Graph Neural Networks in Histopathology: Emerging Trends and Future Directions](https://mlsanity.com/paper/2406.12808/) (2024)
- [A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation](https://mlsanity.com/paper/2502.06895/) (2025)
- [LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation](https://mlsanity.com/paper/2404.05911/) (2024)
- [Exploring 3D U-Net Training Configurations and Post-Processing Strategies for the MICCAI 2023 Kidney and Tumor Segmentation Challenge](https://mlsanity.com/paper/2312.05528/) (2023)
- [Pixel-wise Modulated Dice Loss for Medical Image Segmentation](https://mlsanity.com/paper/2506.15744/) (2025)
- [PSO-UNet: Particle Swarm-Optimized U-Net Framework for Precise Multimodal Brain Tumor Segmentation](https://mlsanity.com/paper/2503.19152/) (2025)
- [Submanifold Sparse Convolutional Networks for Automated 3D Segmentation of Kidneys and Kidney Tumours in Computed Tomography](https://mlsanity.com/paper/2511.04334/) (2025)
- [LiMT: A Multi-task Liver Image Benchmark Dataset](https://mlsanity.com/paper/2511.19889/) (2025)

## Built on by (most cited first, 1 of 1)

- [SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation](https://mlsanity.com/paper/2606.24935/) (2026)

## Abstract (arXiv)

Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class imbalance -- dense, full-resolution inference scales poorly and forces most pipelines to rely on fixed regionization or downsampling, coupling computational cost to image resolution and attenuating boundary evidence precisely where minority structures are most informative. We introduce SEMIR (Semantic Minor-Induced Representation Learning), a representation framework that decouples inference from the native grid by learning a task-adapted, topology-preserving latent graph representation with exact decoding. SEMIR transforms the underlying grid graph into a compact, boundary-aligned graph minor through parameterized edge contraction, node deletion, and edge deletion, while preserving an exact lifting map from minor predictions to lattice labels. Minor construction is formalized as a few-shot structure learning problem that replaces hand-tuned preprocessing with a boundary-alignment objective: minor parameters are learned by maximizing agreement between predicted boundary elements and target-specific semantic edges under a boundary Dice criterion, and the induced minor is annotated with scale- and rotation-robust geometric and intensity descriptors and supports efficient region-level inference via message passing on a graph neural network (GNN) with relational edge features. We benchmark SEMIR on three tumor segmentation datasets -- BraTS 2021, KiTS23, and LiTS -- where targets exhibit high structural variability and distributional uncertainty. SEMIR yields consistent improvements in minority-structure Dice at practical runtime. More broadly, SEMIR establishes a framework for learning task-adapted, topology-preserving latent representations with exact decoding for high-resolution structured visual data.