提出新框架提升前向-前向算法的层次协同与语义清晰度
HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm
- 分层渐进学习，从低级特征到高级语义逐步引导
- 引入对比损失，使分类特征更具区分性，准确率提升超12%
- 适合想改进前向训练模型性能的研究者
基于反向传播的深度神经网络在视觉任务中表现优异，但存在生物不合理、计算开销大和可解释性差的问题。前向-前向（FF）算法通过局部优度目标独立训练每层，提供了一种替代方案。然而，其纯局部优化缺乏层间协调，且优度与特征解耦导致表征无约束、语义模糊。本文提出分层与对比学习的前向-前向框架（HCL-FF），引入（1）从粗到细的层次学习策略，引导表征由低层线索逐步过渡到高层语义；（2）监督对比目标，在优度解耦后强化类别可区分性对齐。在CIFAR-10、CIFAR-100和Tiny-ImageNet上的实验表明，HCL-FF在基于FF的方法中达到新的最先进水平，准确率分别提升+5.46%、+17.00%和+12.51%。
原文摘要 · Abstract (English)
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.
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。