HCL-FF：面向前向-前向算法的层级与对比学习
HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm
为视觉分类网络提供一种不依赖反向传播的逐层局部训练范式，其粗到细层级引导与 goodness 解耦后的监督对比对齐可直接嵌入现有 FF 类训练流程以提升表征判别性。
原文依据 a supervised contrastive objective that enforces class-discriminative alignment after goodness decoupling
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论使用反向传播训练的深度神经网络在视觉任务中取得了卓越性能，但仍存在生物合理性不足、计算开销大以及难以解释的问题。前向-前向（Forward-Forward，FF）算法通过局部 goodness 目标独立训练每一层，提供了一种有前景的替代方案。然而，其纯局部优化缺乏跨层的层级协调，且 goodness 与特征的解耦使表征缺乏约束、语义模糊。我们提出层级与对比学习 FF 框架（HCL-FF）以解决这些局限。HCL-FF 引入：（1）由粗到细的层级学习策略，引导表征从低层线索走向高层语义；（2）监督对比目标，在 goodness 解耦后施加类别判别性对齐。在 CIFAR-10、CIFAR-100 和 Tiny-ImageNet 上的实验表明，HCL-FF 在基于 FF 的方法中取得了新的最优性能，准确率分别显著提升 +5.46%、+17.00% 和 +12.51%。
英文原文摘要 1113 字符
Deep neural networks trained with backpropagation have achieved outstanding performance in vision tasks but remain biologically implausible, computationally demanding, and difficult to interpret. The Forward-Forward (FF) algorithm offers a promising alternative by training each layer independently through local goodness objectives. However, its purely local optimization lacks hierarchical coordination across layers, and the decoupling of goodness from features leaves the representations unconstrained and semantically ambiguous. We propose a Hierarchical and Contrastive Learning FF framework (HCL-FF) to address these limitations. HCL-FF introduces (1) a coarse-to-fine hierarchical learning strategy that guides representations from low-level cues to high-level semantics, and (2) a supervised contrastive objective that enforces class-discriminative alignment after goodness decoupling. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that HCL-FF achieves new state-of-the-art performance among FF-based methods, with notable accuracy gains of +5.46%, +17.00%, and +12.51%, respectively.