# The Role of Recurrency in Image Segmentation for Noisy and Limited Sample Settings

arXiv: https://arxiv.org/abs/2412.15734 · HTML: https://mlsanity.com/paper/2412.15734/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [Dense Associative Memory for Pattern Recognition](https://mlsanity.com/paper/1606.01164/) (2016)
- [Neural Enhanced Belief Propagation on Factor Graphs](https://mlsanity.com/paper/2003.01998/) (2020)
- [Hierarchical Associative Memory](https://mlsanity.com/paper/2107.06446/) (2021)
- [Belief Propagation Neural Networks](https://mlsanity.com/paper/2007.00295/) (2020)
- [Stable and expressive recurrent vision models](https://mlsanity.com/paper/2005.11362/) (2020)
- [Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity](https://mlsanity.com/paper/2310.18894/) (2023)
- [Computing a human-like reaction time metric from stable recurrent vision models](https://mlsanity.com/paper/2306.11582/) (2023)
- [Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations](https://mlsanity.com/paper/2312.14359/) (2023)

## Abstract (arXiv)

The biological brain has inspired multiple advances in machine learning. However, most state-of-the-art models in computer vision do not operate like the human brain, simply because they are not capable of changing or improving their decisions/outputs based on a deeper analysis. The brain is recurrent, while these models are not. It is therefore relevant to explore what would be the impact of adding recurrent mechanisms to existing state-of-the-art architectures and to answer the question of whether recurrency can improve existing architectures. To this end, we build on a feed-forward segmentation model and explore multiple types of recurrency for image segmentation. We explore self-organizing, relational, and memory retrieval types of recurrency that minimize a specific energy function. In our experiments, we tested these models on artificial and medical imaging data, while analyzing the impact of high levels of noise and few-shot learning settings. Our results do not validate our initial hypothesis that recurrent models should perform better in these settings, suggesting that these recurrent architectures, by themselves, are not sufficient to surpass state-of-the-art feed-forward versions and that additional work needs to be done on the topic.