Abstract
Most existing convolutional dictionary learning (CDL) algorithms are based on batch learning, where the dictionary filters and the convolutional sparse representations are optimized in an alternating manner using a training dataset. When large training datasets are used, batch CDL algorithms become prohibitively memory-intensive. An online-learning technique is used to reduce the memory requirements of CDL by optimizing the dictionary incrementally after finding the sparse representations of each training sample. Nevertheless, learning large dictionaries using the existing online CDL (OCDL) algorithms remains highly computationally expensive. In this paper, we present a novel approximate OCDL method that incorporates sparse decomposition of the training samples. The resulting optimization problems are addressed using the alternating direction method of multipliers. Extensive experimental evaluations using several image datasets show that the proposed method substantially reduces computational costs while preserving the effectiveness of the state-of-the-art OCDL algorithms.
Abstract (translated)
大多数现有的卷积词典学习算法(CDL)基于批量学习,在批量训练数据上,字典过滤器和卷积稀疏表示以交替方式优化。当使用大型训练数据集时,批量CDL算法变得非常内存密集型。使用在线学习技术,可以以减少CDL的记忆要求,通过逐步优化字典,在发现每个训练样本的稀疏表示后进行优化。然而,使用现有的在线CDL(OCDL)算法学习大型字典仍然非常计算昂贵。在本文中,我们提出了一种新的近似OCL方法,它包括训练样本稀疏分解的稀疏分解。因此,优化问题使用迭代方向乘法器解决。使用多个图像数据集进行广泛的实验评估,表明, proposed方法极大地减少了计算成本,同时保留了最先进的OCL算法的效果。
URL
https://arxiv.org/abs/2301.10583
