报 告 题 目：Revisiting Sparse Convolutional Model for Visual Recognition

主 讲 人：戴 锡 笠

单 位：香港科技大学

时 间：11月13日10:00

腾 讯 ID: 685-423-697

摘 要：

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be expressed by a linear combination of a few elements from a convolutional dictionary, are powerful tools for analyzing natural images with good theoretical interpretability and biological plausibility. However, such principled models have not demonstrated competitive performance when compared with empirically designed deep networks. This paper revisits the sparse convolutional modeling for image classification and bridges the gap between good empirical performance (of deep learning) and good interpretability (of sparse convolutional models). Our method uses differentiable optimization layers that are defined from convolutional sparse coding as drop-in replacements of standard convolutional layers in conventional deep neural networks. We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks. By leveraging stable recovery property of sparse modeling, we further show that such models can be much more robust to input corruptions as well as adversarial perturbations in testing through a simple proper trade-off between sparse regularization and data reconstruction terms.

简 介：

戴锡笠，香港科技大学(广州)博士，加州大学伯克利分校访问学者（合作导师：马毅教授）。主要研究方向为压缩感知和闭环转录方法在计算机视觉方面的应用，研究成果发表于NeuroIPS、ICLR、TNNLS、AAAI和NeuroComputing等期刊和会议。