44 citations · 241 across the 27 of their papers we have counts for
27 papers
Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
Gen Li, Jie Ji, Minghai Qin +5
As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscali…
DISCO: Distributed Inference with Sparse Communications
Minghai Qin, Chao Sun, Jaco Hofmann +1
Deep neural networks (DNNs) have great potential to solve many real-world problems, but they usually require an extensive amount of computation and memory. It is of great difficult…
All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management
Yifan Gong, Zheng Zhan, Pu Zhao +6
During the deployment of deep neural networks (DNNs) on edge devices, many research efforts are devoted to the limited hardware resource. However, little attention is paid to the i…
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Zhenglun Kong, Haoyu Ma, Geng Yuan +12
Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit the…
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
Sizhe Chen, Geng Yuan, Xinwen Cheng +4
As data becomes increasingly vital, a company would be very cautious about releasing data, because the competitors could use it to train high-performance models, thereby posing a t…
Data Level Lottery Ticket Hypothesis for Vision Transformers
Xuan Shen, Zhenglun Kong, Minghai Qin +6
The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initialization method called the win…
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Yushu Wu, Yifan Gong, Pu Zhao +7
Deep learning-based super-resolution (SR) has gained tremendous popularity in recent years because of its high image quality performance and wide application scenarios. However, pr…
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…
Shfl-BW: Accelerating Deep Neural Network Inference with Tensor-Core Aware Weight Pruning
Guyue Huang, Haoran Li, Minghai Qin +3
Weight pruning in deep neural networks (DNNs) can reduce storage and computation cost, but struggles to bring practical speedup to the model inference time. Tensor-cores can signif…
Adaptive Read Thresholds for NAND Flash
Borja Peleato, Rajiv Agarwal, John Cioffi +2
A primary source of increased read time on NAND flash comes from the fact that in the presence of noise, the flash medium must be read several times using different read threshold…
Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Minghai Qin, Tianyun Zhang, Fei Sun +4
Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them fr…
Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks
Fei Sun, Minghai Qin, Tianyun Zhang +6
Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge de…
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Zhenglun Kong, Peiyan Dong, Xiaolong Ma +9
Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in ind…
Molecular Contrastive Learning with Chemical Element Knowledge Graph
Yin Fang, Qiang Zhang, Haihong Yang +7
Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive…
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
Geng Yuan, Xiaolong Ma, Wei Niu +13
Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory…
Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Xiaolong Ma, Geng Yuan, Xuan Shen +8
There have been long-standing controversies and inconsistencies over the experiment setup and criteria for identifying the "winning ticket" in literature. To reconcile such, we rev…
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Xiaolong Ma, Minghai Qin, Fei Sun +7
Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation res…
Computation on Sparse Neural Networks: an Inspiration for Future Hardware
Fei Sun, Minghai Qin, Tianyun Zhang +3
Neural network models are widely used in solving many challenging problems, such as computer vision, personalized recommendation, and natural language processing. Those models are…
A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods
Tianyun Zhang, Xiaolong Ma, Zheng Zhan +7
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categ…
Learning in the Frequency Domain
Kai Xu, Minghai Qin, Fei Sun +3
Deep neural networks have achieved remarkable success in computer vision tasks. Existing neural networks mainly operate in the spatial domain with fixed input sizes. For practical…
Non-Volatile Memory Array Based Quantization- and Noise-Resilient LSTM Neural Networks
Wen Ma, Pi-Feng Chiu, Won Ho Choi +3
In cloud and edge computing models, it is important that compute devices at the edge be as power efficient as possible. Long short-term memory (LSTM) neural networks have been wide…
Noisy Computations during Inference: Harmful or Helpful?
Minghai Qin, Dejan Vucinic
We study two aspects of noisy computations during inference. The first aspect is how to mitigate their side effects for naturally trained deep learning systems. One of the motivati…
Training Recurrent Neural Networks against Noisy Computations during Inference
Minghai Qin, Dejan Vucinic
We explore the robustness of recurrent neural networks when the computations within the network are noisy. One of the motivations for looking into this problem is to reduce the hig…
Densely Connected High Order Residual Network for Single Frame Image Super Resolution
Yiwen Huang, Ming Qin
Deep convolutional neural networks (DCNN) have been widely adopted for research on super resolution recently, however previous work focused mainly on stacking as many layers as pos…