Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we cannot only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

翻译：尽管深度学习系统在过去十年取得了显著成功，但神经网络与人类决策之间仍存在一个关键差异：作为人类，我们不仅能够当场形成决策，还能通过深入思考，从不同角度重新审视初始猜测，提炼相关信息，最终获得更优决策。本文提出RecycleNet——一种潜在特征循环方法，赋予神经网络反思能力，使其能够通过迭代的循环步骤逐步优化初始决策，其中输出结果以迭代方式反馈回网络早期层。该方法对神经网络架构的假设要求极低，因此可广泛应用于多种场景。以医学图像分割作为评估场景，我们证明潜在特征循环使网络即使在训练期间未见过的迭代次数下，也能迭代精炼初始预测结果，并收敛至更优决策。我们在多个分割基准上进行了评估，即使与顶级分割方法相比，也展现出持续改进效果。这种方法允许以增加计算时间为代价换取性能提升，这在安全关键应用中尤其具有价值。