ZFZhipeng Fan

Zhipeng Fan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zhipeng Fan has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Progressive Channel-Shrinking Network

    by Jianhong Pan, Siyuan Yang, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Zhipeng Fan, Jun Liu

    Currently, salience-based channel pruning makes continuous breakthroughs in network compression. In the realization, the salience mechanism is used as a metric of channel salience to guide pruning. Therefore, salience-based channel pruning can dynamically adjust the channel width at run-time, which provides a flexible pruning scheme. However, there are two problems emerging: a gating function is often needed to truncate the specific salience entries to zero, which destabilizes the forward propagation; dynamic architecture brings more cost for indexing in inference which bottlenecks the inference speed. In this paper, we propose a Progressive Channel-Shrinking (PCS) method to compress the selected salience entries at run-time instead of roughly approximating them to zero. We also propose a Running Shrinking Policy to provide a testing-static pruning scheme that can reduce the memory access cost for filter indexing. We evaluate our method on ImageNet and CIFAR10 datasets over two prevalent networks: ResNet and VGG, and demonstrate that our PCS outperforms all baselines and achieves state-of-the-art in terms of compression-performance tradeoff. Moreover, we observe a significant and practical acceleration of inference. The code will be released upon acceptance.


  • Open Access

    System-status-aware Adaptive Network for Online Streaming Video Understanding

    by Lin Geng Foo, Jia Gong, Zhipeng Fan, Jun Liu

    Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over time, and none of them investigate or address the impact of varying computational resources for online video understanding tasks. This paper proposes a System-status-aware Adaptive Network (SAN) that considers the device's real-time state to provide high-quality predictions with low delay. Usage of our agent's policy improves efficiency and robustness to fluctuations of the system status. On two widely used video understanding tasks, SAN obtains state-of-the-art performance while constantly keeping processing delays low. Moreover, training such an agent on various types of hardware configurations is not easy as the labeled training data might not be available, or can be computationally prohibitive. To address this challenging problem, we propose a Meta Self-supervised Adaptation (MSA) method that adapts the agent's policy to new hardware configurations at test-time, allowing for easy deployment of the model onto other unseen hardware platforms.

  • Open Access

    DiffPose: Toward More Reliable 3D Pose Estimation

    by Jia Gong, Lin Geng Foo, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu

    Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity and occlusion, which often lead to high uncertainty and indeterminacy. On the other hand, diffusion models have recently emerged as an effective tool for generating high-quality images from noise. Inspired by their capability, we explore a novel pose estimation framework (DiffPose) that formulates 3D pose estimation as a reverse diffusion process. We incorporate novel designs into our DiffPose to facilitate the diffusion process for 3D pose estimation: a pose-specific initialization of pose uncertainty distributions, a Gaussian Mixture Model-based forward diffusion process, and a context-conditioned reverse diffusion process. Our proposed DiffPose significantly outperforms existing methods on the widely used pose estimation benchmarks Human3.6M and MPI-INF-3DHP. Project page: https://gongjia0208.github.io/Diffpose/.

  • GradMDM: Adversarial Attack on Dynamic Networks

    by Jianhong Pan, Lin Geng Foo, Qichen Zheng, Zhipeng Fan, Hossein Rahmani, Qiuhong Ke, Jun Liu

    Dynamic neural networks can greatly reduce computation redundancy without compromising accuracy by adapting their structures based on the input. In this paper, we explore the robustness of dynamic neural networks against energy-oriented attacks targeted at reducing their efficiency. Specifically, we attack dynamic models with our novel algorithm GradMDM. GradMDM is a technique that adjusts the direction and the magnitude of the gradients to effectively find a small perturbation for each input, that will activate more computational units of dynamic models during inference. We evaluate GradMDM on multiple datasets and dynamic models, where it outperforms previous energy-oriented attack techniques, significantly increasing computation complexity while reducing the perceptibility of the perturbations https://github.com/lingengfoo/GradMDM .


  • Analysis and comparison of optimization method for comparator design

    by Zhipeng Fan, Zeheng Yang, Fei Zhang

    The comparator is essential in analog-to-digital converters (ADC). This paper analyzes different improvements in the designs of comparators. In order to improve the energy efficiency, the dynamic bias comparator was developed, and it also reduces the input-referred noise. A floating reservoir design was then adopted to solve some weaknesses of the dynamic bias comparator and further increases energy efficiency. On-chip inductors and charge pumps were also implemented to perfect the performance of the comparator. These two changes improve delay performance, and the first one reduces power consumption simultaneously. The last update was an energy-efficient ring oscillator collapse-based comparator. It adjusts the performance of the comparator without any external control and then makes the energy consumption achieve a minimum value without energy scaling. At the same time, this comparator has a wider resolution tuning capability.

  • GradAuto: Energy-Oriented Attack on Dynamic Neural Networks

    by Jianhong Pan, Qichen Zheng, Zhipeng Fan, Hossein Rahmani, Qiuhong Ke, Jun Liu