报告题目：revisiting sparse convolutional modeling for visual recognition
主 讲 人： 戴锡笠 香港科技大学（广州）
报告时间：2023年02月13日（星期一）8:30-10:30
报告地点：腾讯会议：100-724-167
报告摘要：
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.
报告人简介：
xili dai is a ph.d. student in hkust(gz), advised by prof.yi ma of uc berkeley, prof. harry shum and prof. lionel ni of hkust(gz). his research interests lying on the intersection among closed loop transcription via rate reduction, 3d vision, sparse coding, and dictionary learning. his recent research focuses on 3d reconstruction via closed loop rate reduction.
(personal homepage. photo could be found here. )
邀请人：信息与通信工程系 孙海信教授