将传统稀疏模型与深度架构结合，实现高效可解释的图像分类。
Semi-Unified Sparse Dictionary Learning with Learnable Top-K LISTA and FISTA Encoders
- 用可学习Top-K的LISTA和FISTA编码器统一稀疏字典学习框架
- 在CIFAR-10上达95.6%准确率，内存低于4GB GPU
- 兼顾可解释性与训练效率，适合追求透明性的模型设计
我们提出一种半统一稀疏字典学习框架，连接经典稀疏模型与现代深度架构。具体地，将严格的Top-K LISTA及其凸型变体LISTAConv集成到判别式LC-KSVD2模型中，使稀疏编码器与字典在监督或无监督设置下协同演化。该统一设计保留了传统稀疏编码的可解释性，同时支持高效、可微分训练。我们进一步为凸变体建立了类PALM的收敛性分析，确保块交替优化下的理论稳定性。实验表明，所提LC-KSVD2 + LISTA/LISTAConv管道在CIFAR-10上达到95.6%、CIFAR-100上86.3%、TinyImageNet上88.5%的准确率，收敛更快且显存消耗低于4GB GPU。结果验证了该方法是现代深度架构的一种可解释且计算高效的替代方案。
原文摘要 · Abstract (English)
We present a semi-unified sparse dictionary learning framework that bridges the gap between classical sparse models and modern deep architectures. Specifically, the method integrates strict Top-$K$ LISTA and its convex FISTA-based variant (LISTAConv) into the discriminative LC-KSVD2 model, enabling co-evolution between the sparse encoder and the dictionary under supervised or unsupervised regimes. This unified design retains the interpretability of traditional sparse coding while benefiting from efficient, differentiable training. We further establish a PALM-style convergence analysis for the convex variant, ensuring theoretical stability under block alternation. Experimentally, our method achieves 95.6\% on CIFAR-10, 86.3\% on CIFAR-100, and 88.5\% on TinyImageNet with faster convergence and lower memory cost ($<$4GB GPU). The results confirm that the proposed LC-KSVD2 + LISTA/LISTAConv pipeline offers an interpretable and computationally efficient alternative for modern deep architectures.
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。