56 citations · 164 across the 24 of their papers we have counts for
24 papers
MILAN: Masked Image Pretraining on Language Assisted Representation
Zejiang Hou, Fei Sun, Yen-Kuang Chen +2
Self-attention based transformer models have been dominating many computer vision tasks in the past few years. Their superb model qualities heavily depend on the excessively large…
CHEX: CHannel EXploration for CNN Model Compression
Zejiang Hou, Minghai Qin, Fei Sun +7
Channel pruning has been broadly recognized as an effective technique to reduce the computation and memory cost of deep convolutional neural networks. However, conventional pruning…
Multi-Dimensional Model Compression of Vision Transformer
Zejiang Hou, Sun-Yuan Kung
Vision transformers (ViT) have recently attracted considerable attentions, but the huge computational cost remains an issue for practical deployment. Previous ViT pruning methods t…
Class-Discriminative CNN Compression
Yuchen Liu, David Wentzlaff, S. Y. Kung
Compressing convolutional neural networks (CNNs) by pruning and distillation has received ever-increasing focus in the community. In particular, designing a class-discrimination ba…
Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis
Zejiang Hou, Sun-Yuan Kung
We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches r…
A compressive multi-kernel method for privacy-preserving machine learning
Thee Chanyaswad, J. Morris Chang, S. Y. Kung
As the analytic tools become more powerful, and more data are generated on a daily basis, the issue of data privacy arises. This leads to the study of the design of privacy-preserv…
Content-Aware GAN Compression
Yuchen Liu, Zhixin Shu, Yijun Li +3
Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders th…
A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network
Tanvir Mahmud, A. Q. M. Sazzad Sayyed, Shaikh Anowarul Fattah +1
Deep neural network is an effective choice to automatically recognize human actions utilizing data from various wearable sensors. These networks automate the process of feature ext…
CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans
Tanvir Mahmud, Md Awsafur Rahman, Shaikh Anowarul Fattah +1
Automatic lung lesions segmentation of chest CT scans is considered a pivotal stage towards accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-de…
Privacy Enhancing Machine Learning via Removal of Unwanted Dependencies
Mert Al, Semih Yagli, Sun-Yuan Kung
The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data…
A Feature-map Discriminant Perspective for Pruning Deep Neural Networks
Zejiang Hou, Sun-Yuan Kung
Network pruning has become the de facto tool to accelerate deep neural networks for mobile and edge applications. Recently, feature-map discriminant based channel pruning has shown…
Rethinking Class-Discrimination Based CNN Channel Pruning
Yuchen Liu, David Wentzlaff, S. Y. Kung
Channel pruning has received ever-increasing focus on network compression. In particular, class-discrimination based channel pruning has made major headway, as it fits seamlessly w…
Soft-Root-Sign Activation Function
Yuan Zhou, Dandan Li, Shuwei Huo +1
The choice of activation function in deep networks has a significant effect on the training dynamics and task performance. At present, the most effective and widely-used activation…
Exploiting Operation Importance for Differentiable Neural Architecture Search
Xukai Xie, Yuan Zhou, Sun-Yuan Kung
Recently, differentiable neural architecture search methods significantly reduce the search cost by constructing a super network and relax the architecture representation by assign…
Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking
Yuan Zhou, Xiaoting Du, Yeda Zhang +1
In general, image restoration involves mapping from low quality images to their high-quality counterparts. Such optimal mapping is usually non-linear and learnable by machine learn…
Temporal Action Localization using Long Short-Term Dependency
Yuan Zhou, Hongru Li, Sun-Yuan Kung
Temporal action localization in untrimmed videos is an important but difficult task. Difficulties are encountered in the application of existing methods when modeling temporal stru…
Comb Convolution for Efficient Convolutional Architecture
Dandan Li, Yuan Zhou, Shuwei Huo +1
Convolutional neural networks (CNNs) are inherently suffering from massively redundant computation (FLOPs) due to the dense connection pattern between feature maps and convolution…
Scalable Kernel Learning via the Discriminant Information
Mert Al, Zejiang Hou, Sun-Yuan Kung
Kernel approximation methods create explicit, low-dimensional kernel feature maps to deal with the high computational and memory complexity of standard techniques. This work studie…
HGC: Hierarchical Group Convolution for Highly Efficient Neural Network
Xukai Xie, Yuan Zhou, Sun-Yuan Kung
Group convolution works well with many deep convolutional neural networks (CNNs) that can effectively compress the model by reducing the number of parameters and computational cost…
Supervising Nyström Methods via Negative Margin Support Vector Selection
Mert Al, Thee Chanyaswad, Sun-Yuan Kung
The Nyström methods have been popular techniques for scalable kernel based learning. They approximate explicit, low-dimensional feature mappings for kernel functions from the pairw…
Protecting Genomic Privacy by a Sequence-Similarity Based Obfuscation Method
Shibiao Wan, Man-Wai Mak, Sun-Yuan Kung
In the post-genomic era, large-scale personal DNA sequences are produced and collected for genetic medical diagnoses and new drug discovery, which, however, simultaneously poses se…
Desensitized RDCA Subspaces for Compressive Privacy in Machine Learning
Artur Filipowicz, Thee Chanyaswad, S. Y. Kung
The quest for better data analysis and artificial intelligence has lead to more and more data being collected and stored. As a consequence, more data are exposed to malicious entit…
Ratio Utility and Cost Analysis for Privacy Preserving Subspace Projection
Mert Al, Shibiao Wan, Sun-Yuan Kung
With a rapidly increasing number of devices connected to the internet, big data has been applied to various domains of human life. Nevertheless, it has also opened new venues for b…
Efficient Divide-And-Conquer Classification Based on Feature-Space Decomposition
Qi Guo, Bo-Wei Chen, Feng Jiang +2
This study presents a divide-and-conquer (DC) approach based on feature space decomposition for classification. When large-scale datasets are present, typical approaches usually em…