Zhihang Yuan

Zhihang Yuan

Auto-generated profile, based on publicly available information

Zhihang Yuan

Peking University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2022
Verified
Book Chapter
Closed access
PDF file
ZYZhihang Yuan
Zhihang Yuan
CXChenhao Xue
Chenhao Xue
YCYiqi Chen
Yiqi Chen
QWQiang Wu
Qiang Wu
Guangyu SunGuangyu Sun
Guangyu Sun

25 April 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YHYizeng Han
Yizeng Han
ZLZeyu Liu
Zeyu Liu
ZYZhihang Yuan
Zhihang Yuan
YPYifan Pu
Yifan Pu
CWChaofei Wang
Chaofei Wang
GHGao Huang
Gao Huang
Dynamic computation has emerged as a promising strategy to improve the inference efficiency of deep networks. It allows selective activation of various computing units, such as layers or convolution channels, or adaptive allocation of computation to highly informative spatial regions in image features, thus significantly reducing unnecessary computations conditioned on each input sample. However, the practical efficiency of dynamic models does not always correspond to theoretical outcomes. This discrepancy stems from three key challenges: 1) The absence of a unified formulation for various dynamic inference paradigms, owing to the fragmented research landscape; 2) The undue emphasis on algorithm design while neglecting scheduling strategies , which are critical for optimizing computational performance and resource utilization in CUDA-enabled GPU settings; and 3) The cumbersome process of evaluating practical latency, as most existing libraries are tailored for static operators. To address these issues, we introduce Latency-Aware Unified Dynamic Networks (LAUDNet) , a comprehensive framework that amalgamates three cornerstone dynamic paradigms-spatially-adaptive computation, dynamic layer skipping, and dynamic channel skipping-under a unified formulation. To reconcile theoretical and practical efficiency, LAUDNet integrates algorithmic design with scheduling optimization, assisted by a latency predictor that accurately and efficiently gauges the inference latency of dynamic operators. This latency predictor harmonizes considerations of algorithms, scheduling strategies, and hardware attributes. We empirically validate various dynamic paradigms within the LAUDNet framework across a range of vision tasks, including image classification, object detection, and instance segmentation. Our experiments confirm that LAUDNet effectively narrows the gap between theoretical and real-world efficiency. For example, LAUDNet can reduce the practical latency of its static counterpart, ResNet-101, by over 50% on hardware platforms such as V100, RTX3090, and TX2 GPUs. Furthermore, LAUDNet surpasses competing methods in the trade-off between accuracy and efficiency. Code is available at: https://www.github.com/LeapLabTHU/LAUDNet .


9 November 2023 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
XWXiaoyang Wang
Xiaoyang Wang
ZZZhe Zhou
Zhe Zhou
ZYZhihang Yuan
Zhihang Yuan
JZJingchen Zhu
Jingchen Zhu
YCYulong Cao
Yulong Cao
Guangyu SunGuangyu Sun
Guangyu Sun
In the emerging edge-computing scenarios, FPGAs have been widely adopted to accelerate convolutional neural network (CNN)–based image-processing applications, such as image classification, object detection, and image segmentation, and so on. A standard image-processing pipeline first decodes the collected compressed images from Internet of Things (IoTs) to RGB data, then feeds them into CNN engines to compute the results. Previous works mainly focus on optimizing the CNN inference parts. However, we notice that on the popular ZYNQ FPGA platforms, image decoding can also become the bottleneck due to the poor performance of embedded ARM CPUs. Even with a hardware accelerator, the decoding operations still incur considerable latency. Moreover, conventional RGB-based CNNs have too few input channels at the first layer, which can hardly utilize the high parallelism of CNN engines and greatly slows down the network inference. To overcome these problems, in this article, we propose FD-CNN, a novel CNN accelerator leveraging the partial-decoding technique to accelerate CNNs directly in the frequency domain. Specifically, we omit the most time-consuming IDCT (Inverse Discrete Cosine Transform) operations of image decoding and directly feed the DCT coefficients (i.e., the frequency data) into CNNs. By this means, the image decoder can be greatly simplified. Moreover, compared to the RGB data, frequency data has a narrower input resolution but has 64× more channels. Such an input shape is more hardware friendly than RGB data and can substantially reduce the CNN inference time. We then systematically discuss the algorithm, architecture, and command set design of FD-CNN. To deal with the irregularity of different CNN applications, we propose an image-decoding-aware design-space exploration (DSE) workflow to optimize the pipeline. We further propose an early stopping strategy to tackle the time-consuming progressive JPEG decoding. Comprehensive experiments demonstrate that FD-CNN achieves, on average, 3.24×, 4.29× throughput improvement, 2.55×, 2.54× energy reduction and 2.38×, 2.58× lower latency on ZC-706 and ZCU-102 platforms, respectively, compared to the baseline image-processing pipelines.

18 March 2020 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
YGYijin Guan
Yijin Guan
Guangyu SunGuangyu Sun
Guangyu Sun
ZYZhihang Yuan
Zhihang Yuan
XLXingchen Li
Xingchen Li
NXNingyi Xu
Ningyi Xu
YXYuan Xie
Yuan Xie
Convolutional neural networks (CNNs) have achieved great success in numerous AI applications. To improve inference efficiency of CNNs, researchers have proposed various pruning techniques to reduce both computation intensity and storage overhead. These pruning techniques result in multi-level sparsity irregularities in CNNs. Together with that in activation matrices, which is induced by employment of ReLU activation function, all these sparsity irregularities cause a serious problem of computation resource under-utilization in sparse CNN accelerators. To mitigate this problem, we propose a method of load-balancing based on a workload stealing technique. We demonstrate that this method can be applied to two major inference data-flows, which cover all state-of-the-art sparse CNN accelerators. Based on this method, we present an accelerator, called Crane, which addresses all kinds of sparsity irregularities in CNNs. We perform a fair comparison between Crane and state-of-the-art prior approaches. Experimental results show that Crane improves performance by 27%∼88% and reduces energy consumption by 16%∼48%, respectively, compared to the counterparts.

27 October 2025
Verified
Conference Paper
Open access
ZYZhihang Yuan
Zhihang Yuan
SWSiyuan Wang
Siyuan Wang
YSYuzhang Shang
Yuzhang Shang
HZHanling Zhang
Hanling Zhang
TFTongcheng Fang
Tongcheng Fang
YWYu Wang
Yu Wang