基于信息瓶颈的自适应卷积稀疏编码用于鲁棒视觉信号表示
Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation
- Shenzhen University of Advanced Technology（深圳理工大学）
- University of Electronic Science and Technology of China（电子科技大学）
- Shandong University（山东大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出自适应卷积稀疏编码框架，通过信息瓶颈动态调整稀疏系数，结合FISTA展开与后训练策略，在CIFAR和ImageNet上显著提升鲁棒性。
AI中文摘要：
视觉信号需要紧凑且充分的表示以实现鲁棒的下游预测。卷积稀疏编码（CSC）提供了一种显式机制，用于抑制冗余分量同时保留信号内容，但其稀疏系数通常是固定的且需手动选择。我们提出了一种用于鲁棒视觉信号表示的自适应卷积稀疏编码框架。具体而言，我们使用快速迭代收缩阈值算法（FISTA）展开CSC优化，并将稀疏系数视为可微变量，与网络参数联合学习。从信息瓶颈的角度来看，该系数控制信息保留与压缩之间的权衡：稀疏项促进紧凑表示，而重建项连同任务损失保留与任务相关的信号内容。我们进一步引入了一种无标签的后训练策略，该策略在主网络参数固定的情况下，针对受损输入调整压缩强度。在CIFAR和ImageNet上的实验表明，该方法在干净数据识别上具有竞争力，并在不同输入扰动下大幅提升了鲁棒性。
英文摘要：
Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is often manually selected during training. We propose a training-adaptive convolutional sparse coding framework for robust visual signal representation. Specifically, we unfold the CSC optimization with the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) and treat the sparsity coefficient as a differentiable variable jointly learned with the network parameters. From the information bottleneck perspective, this coefficient controls the trade-off between information retention and compression: the sparsity term promotes compact representations, while the reconstruction term together with task loss preserves task-relevant signal content. We further introduce a label-free post-training strategy that adjusts the compression strength for corrupted inputs with the main network parameters fixed. Experiments on CIFAR and ImageNet demonstrate competitive clean-data recognition and greatly improved robustness under different input perturbations.
