Deep Recurrence for Dynamical Segmentation Models
This work addresses the need for more adaptive and biologically plausible neural networks in computer vision, though it is incremental as it builds on existing U-Net architectures.
The paper tackled the problem of improving segmentation models' robustness and data efficiency by introducing a biologically inspired feedback mechanism, achieving above random performance with only two training examples compared to four required by feedforward models.
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.