给神经网络加反馈回路，让模型像人一样迭代修正判断。
Deep Recurrence for Dynamical Segmentation Models
- 用生物启发的反馈机制，在输出与输入间形成循环迭代。
- 仅需2个样本就超越随机水平，比前馈模型少2个样本即可达标。
- 适合追求鲁棒性与数据效率的视觉建模研究者。
尽管生物视觉系统依赖反馈连接进行感知迭代优化，大多数人工神经网络仍为纯前馈结构，仅单次静态处理输入。本文提出一种受预测编码启发的反馈机制，引入从输出到输入的循环路径，使模型能随时间逐步优化内部状态。在标准U-Net架构中实现该机制，并引入两种生物启发操作——软最大投影与指数衰减，以保证反馈循环稳定。在合成分割任务的对照实验中，反馈模型在噪声环境下显著优于前馈模型，且在有限监督下泛化能力更强。值得注意的是，反馈模型仅用两个训练样本即达到高于随机性能，而前馈模型至少需四个样本。结果表明，反馈机制提升了鲁棒性与数据效率，为构建更自适应、更符合生物原理的神经网络提供了路径。代码已开源：github.com/DCalhas/feedback_segmentation。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。