Saved in:
Bibliographic Details
Main Authors: Calhas, David, Oliveira, Arlindo L.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.10143
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915388649897984
author Calhas, David
Oliveira, Arlindo L.
author_facet Calhas, David
Oliveira, Arlindo L.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10143
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Recurrence for Dynamical Segmentation Models
Calhas, David
Oliveira, Arlindo L.
Computer Vision and Pattern Recognition
Machine Learning
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.
title Deep Recurrence for Dynamical Segmentation Models
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.10143