Deep Recurrence for Dynamical Segmentation Models

TL;DR

This paper introduces a biologically inspired recurrent feedback mechanism within a U-Net architecture that improves robustness and data efficiency in segmentation tasks, especially under noisy conditions and limited supervision.

Contribution

It proposes a novel feedback loop inspired by predictive coding, with stability mechanisms, to enhance segmentation models beyond traditional feedforward approaches.

Findings

Feedback model outperforms feedforward in noisy conditions

Feedback achieves above random performance with only two training examples

Model generalizes better with limited supervision

Abstract

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.