# Deep Recurrence for Dynamical Segmentation Models

arXiv: https://arxiv.org/abs/2507.10143 · HTML: https://mlsanity.com/paper/2507.10143/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Deep Equilibrium Models](https://mlsanity.com/paper/1909.01377/) (2019)
- [Dense Associative Memory for Pattern Recognition](https://mlsanity.com/paper/1606.01164/) (2016)
- [A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions](https://mlsanity.com/paper/1705.02498/) (2017)
- [Energy Transformer](https://mlsanity.com/paper/2302.07253/) (2023)
- [Reviving and Improving Recurrent Back-Propagation](https://mlsanity.com/paper/1803.06396/) (2018)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [A simple way to make neural networks robust against diverse image corruptions](https://mlsanity.com/paper/2001.06057/) (2020)
- [Stable and expressive recurrent vision models](https://mlsanity.com/paper/2005.11362/) (2020)
- [Feasibility-based Fixed Point Networks](https://mlsanity.com/paper/2104.14090/) (2021)
- [Computing a human-like reaction time metric from stable recurrent vision models](https://mlsanity.com/paper/2306.11582/) (2023)
- [On the role of feedback in visual processing: a predictive coding perspective](https://mlsanity.com/paper/2106.04225/) (2021)

## Abstract (arXiv)

While biological vision systems rely heavily on feedback connections to iteratively refine perception, most artificial neural networks remain purely feedforward, processing input in a single static pass. In this work, we propose a predictive coding inspired feedback mechanism that introduces a recurrent loop from output to input, allowing the model to refine its internal state over time. We implement this mechanism within a standard U-Net architecture and introduce two biologically motivated operations, softmax projection and exponential decay, to ensure stability of the feedback loop. Through controlled experiments on a synthetic segmentation task, we show that the feedback model significantly outperforms its feedforward counterpart in noisy conditions and generalizes more effectively with limited supervision. Notably, feedback achieves above random performance with just two training examples, while the feedforward model requires at least four. Our findings demonstrate that feedback enhances robustness and data efficiency, and offer a path toward more adaptive and biologically inspired neural architectures. Code is available at: github.com/DCalhas/feedback_segmentation.