# Multi-level Cellular Automata for FLIM networks

arXiv: https://arxiv.org/abs/2504.11406 · HTML: https://mlsanity.com/paper/2504.11406/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 67 references that are in the map.
- First posted on arXiv 15 Apr 2025.

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

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Salient Object Detection: A Survey](https://mlsanity.com/paper/1411.5878/) (2014)
- [Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network](https://mlsanity.com/paper/2008.05441/) (2020)
- [MoGA: Searching Beyond MobileNetV3](https://mlsanity.com/paper/1908.01314/) (2019)
- [Learning CNN filters from user-drawn image markers for coconut-tree image classification](https://mlsanity.com/paper/2008.03549/) (2020)
- [A lightweight multi-scale context network for salient object detection in optical remote sensing images](https://mlsanity.com/paper/2205.08959/) (2022)
- [Interactive Image Selection and Training for Brain Tumor Segmentation Network](https://mlsanity.com/paper/2406.03225/) (2024)
- [Automated Diagnosis of Intestinal Parasites: A new hybrid approach and its benefits](https://mlsanity.com/paper/2101.06310/) (2021)
- [Hierarchical Cellular Automata for Visual Saliency](https://mlsanity.com/paper/1705.09425/) (2017)

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

- [FLIM Networks with Bag of Feature Points](https://mlsanity.com/paper/2602.20845/) (2026)

## Abstract (arXiv)

The necessity of abundant annotated data and complex network architectures presents a significant challenge in deep-learning Salient Object Detection (deep SOD) and across the broader deep-learning landscape. This challenge is particularly acute in medical applications in developing countries with limited computational resources. Combining modern and classical techniques offers a path to maintaining competitive performance while enabling practical applications. Feature Learning from Image Markers (FLIM) methodology empowers experts to design convolutional encoders through user-drawn markers, with filters learned directly from these annotations. Recent findings demonstrate that coupling a FLIM encoder with an adaptive decoder creates a flyweight network suitable for SOD, requiring significantly fewer parameters than lightweight models and eliminating the need for backpropagation. Cellular Automata (CA) methods have proven successful in data-scarce scenarios but require proper initialization -- typically through user input, priors, or randomness. We propose a practical intersection of these approaches: using FLIM networks to initialize CA states with expert knowledge without requiring user interaction for each image. By decoding features from each level of a FLIM network, we can initialize multiple CAs simultaneously, creating a multi-level framework. Our method leverages the hierarchical knowledge encoded across different network layers, merging multiple saliency maps into a high-quality final output that functions as a CA ensemble. Benchmarks across two challenging medical datasets demonstrate the competitiveness of our multi-level CA approach compared to established models in the deep SOD literature.