116 citations · 430 across the 65 of their papers we have counts for
8 papers · 1 filter
Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs
Yecheng Lyu, Xinming Huang, Ziming Zhang
Graph convolutional networks (GCNs) suffer from the irregularity of graphs, while more widely-used convolutional neural networks (CNNs) benefit from regular grids. To bridge the ga…
White-Box Adversarial Defense via Self-Supervised Data Estimation
Zudi Lin, Hanspeter Pfister, Ziming Zhang
In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous wor…
Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
Xenju Xu, Guanghui Wang, Alan Sullivan +1
In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to…
RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Anil Kag, Ziming Zhang, Venkatesh Saligrama
Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropag…
Unsupervised Deep Feature Transfer for Low Resolution Image Classification
Yuanwei Wu, Ziming Zhang, Guanghui Wang
In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is requi…
Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
Esra Ataer-Cansizoglu, Michael Jones, Ziming Zhang +1
Face super-resolution methods usually aim at producing visually appealing results rather than preserving distinctive features for further face identification. In this work, we prop…
Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability
Ziming Zhang, Anil Kag, Alan Sullivan +1
We propose a novel {\it Equilibrated Recurrent Neural Network} (ERNN) to combat the issues of inaccuracy and instability in conventional RNNs. Drawing upon the concept of autapse i…
Time-Delay Momentum: A Regularization Perspective on the Convergence and Generalization of Stochastic Momentum for Deep Learning
Ziming Zhang, Wenju Xu, Alan Sullivan
In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization. To do so, we first…