# KARMA: Efficient Structural Defect Segmentation via Kolmogorov-Arnold Representation Learning

arXiv: https://arxiv.org/abs/2508.08186 · HTML: https://mlsanity.com/paper/2508.08186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [UNeXt: MLP-based Rapid Medical Image Segmentation Network](https://mlsanity.com/paper/2203.04967/) (2022)
- [U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation](https://mlsanity.com/paper/2406.02918/) (2024)
- [SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation](https://mlsanity.com/paper/2004.03696/) (2020)
- [FasterViT: Fast Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2306.06189/) (2023)
- [rKAN: Rational Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2406.14495/) (2024)
- [A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Data](https://mlsanity.com/paper/2406.14529/) (2024)
- [F-KANs: Federated Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2407.20100/) (2024)
- [KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements](https://mlsanity.com/paper/2410.17172/) (2024)
- [Imbalance-Aware Culvert-Sewer Defect Segmentation Using an Enhanced Feature Pyramid Network](https://mlsanity.com/paper/2408.10181/) (2024)
- [Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation](https://mlsanity.com/paper/2312.14053/) (2023)
- [MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer For Efficient Medical Image Segmentation](https://mlsanity.com/paper/2409.03062/) (2024)
- [A Multitask Deep Learning Model for Parsing Bridge Elements and Segmenting Defect in Bridge Inspection Images](https://mlsanity.com/paper/2209.02190/) (2022)

## Abstract (arXiv)

Semantic segmentation of structural defects in civil infrastructure remains challenging due to variable defect appearances, harsh imaging conditions, and significant class imbalance. Current deep learning methods, despite their effectiveness, typically require millions of parameters, rendering them impractical for real-time inspection systems. We introduce KARMA (Kolmogorov-Arnold Representation Mapping Architecture), a highly efficient semantic segmentation framework that models complex defect patterns through compositions of one-dimensional functions rather than conventional convolutions. KARMA features three technical innovations: (1) a parameter-efficient Tiny Kolmogorov-Arnold Network (TiKAN) module leveraging low-rank factorization for KAN-based feature transformation; (2) an optimized feature pyramid structure with separable convolutions for multi-scale defect analysis; and (3) a static-dynamic prototype mechanism that enhances feature representation for imbalanced classes. Extensive experiments on benchmark infrastructure inspection datasets demonstrate that KARMA achieves competitive or superior mean IoU performance compared to state-of-the-art approaches, while using significantly fewer parameters (0.959M vs. 31.04M, a 97% reduction). Operating at 0.264 GFLOPS, KARMA maintains inference speeds suitable for real-time deployment, enabling practical automated infrastructure inspection systems without compromising accuracy. The source code can be accessed at the following URL: https://github.com/faeyelab/karma.