科研成果 by Type: Conference Paper

2022
Li X, Sun Y, Wu X, Chen J*. Multi-Speaker Pitch Tracking via Embodied Self-Supervised Learning, in 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore City, Singapore; 2022:8257–8261. 代码链接
Yi F, Yang Y, Jiang T. Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition, in The 16th Asian Conference on Computer Vision, ACCV 2022, December 4-8.Vol 13844. Macao, China: Springer; 2022:417–432. 访问链接
Jia T, Yang E-Y, Hsiao Y-S, Cruz J, Brooks D, Wei G-Y, Reddi VJ. OMU: A probabilistic 3D occupancy mapping accelerator for real-time OctoMap at the edge, in Design, Automation and Test in Europe (DATE).; 2022.
Bu T, Fang W, Ding J, Dai P, Yu Z*, Huang T. Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks, in The Tenth International Conference on Learning Representations (ICLR).; 2022.Abstract
Spiking Neural Networks (SNNs) have gained great attraction due to their distinctive properties of low power consumption and fast inference on neuromorphic hardware. As the most effective method to get deep SNNs, ANN-SNN conversion has achieved comparable performance as ANNs on large-scale datasets. Despite this, it requires long time-steps to match the firing rates of SNNs to the activation of ANNs. As a result, the converted SNN suffers severe performance degradation problems with short time-steps, which hamper the practical application of SNNs. In this paper, we theoretically analyze ANN-SNN conversion error and derive the estimated activation function of SNNs. Then we propose the quantization clip-floor-shift activation function to replace the ReLU activation function in source ANNs, which can better approximate the activation function of SNNs. We prove that the expected conversion error between SNNs and ANNs is zero, enabling us to achieve high-accuracy and ultra-low-latency SNNs. We evaluate our method on CIFAR-10/100 and ImageNet datasets, and show that it outperforms the state-of-the-art ANN-SNN and directly trained SNNs in both accuracy and time-steps. To the best of our knowledge, this is the first time to explore high-performance ANN-SNN conversion with ultra-low latency (4 time-steps).
Zhang R, Li S, Wang C, Xie G. Optimal Strategies for the Game with Two Faster 3D Pursuers and One Slower 2D Evader, in 2022 41st Chinese Control Conference (CCC). IEEE; 2022:1767–1772. 访问链接
Hu Q, Li Q, Zhu S, Gu C, Liu S, HUANG R, Wu Y. Optimized IGZO FETs for Capacitorless DRAM with Retention of 10 ks at RT and 7 ks at 85° C at Zero V hold with Sub-10 ns Speed and 3-bit Operation, in 2022 International Electron Devices Meeting (IEDM). IEEE; 2022:26–6.
Bu T, Ding J, Yu Z*, Huang T. Optimized Potential Initialization for Low-latency Spiking Neural Networks, in Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI).; 2022.Abstract
Spiking Neural Networks (SNNs) have been attached great importance due to the distinctive properties of low power consumption,  biological plausibility, and adversarial robustness. The most effective way to train deep SNNs is through ANN-to-SNN conversion, which have yielded the best performance in deep network structure and large-scale datasets. However, there is a trade-off between accuracy and latency. In order to achieve high precision as original ANNs, a long simulation time is needed to match the firing rate of a spiking neuron with the activation value of an analog neuron, which impedes the practical application of SNN. In this paper, we aim to achieve high-performance converted SNNs with extremely low latency (fewer than 32 time-steps). We start by theoretically analyzing ANN-to-SNN conversion and show that scaling the thresholds does play a similar role as weight normalization. Instead of introducing constraints that facilitate ANN-to-SNN conversion at the cost of model capacity, we applied a more direct way by optimizing the initial membrane potential to reduce the conversion loss in each layer. Besides, we demonstrate that optimal initialization of membrane potentials can implement expected error-free ANN-to-SNN conversion. We evaluate our algorithm on the CIFAR-10, CIFAR-100 and ImageNet datasets and achieve state-of-the-art accuracy, using fewer time-steps. For example, we reach top-1 accuracy of 93.38% on CIFAR-10 with 16 time-steps. Moreover, our method can be applied to other ANN-SNN conversion methodologies and remarkably promote performance when the time-steps is small.
Qin W, Xu R, Jiang S, Jiang T, Luo L. PathTR: Context-Aware Memory Transformer for Tumor Localization in Gigapixel Pathology Images, in Asian Conference on Computer Vision, ACCV 2022, December 4-8. Macao, China; 2022:3603-3619. 访问链接
Cheng H, others. The Physics potential of the CEPC. Prepared for the US Snowmass Community Planning Exercise (Snowmass 2021), in Snowmass 2021.; 2022.
Li S, Wang C, Xie G. Pursuit-evasion differential games of players with different speeds in spaces of different dimensions, in 2022 American Control Conference (ACC). IEEE; 2022:1299–1304. 访问链接
Fu T, Zeng M, Liu S, Liu H, HUANG R, Wu Y. Record-high 2P r= 60 $μ$C/cm 2 by Sub-5ns Switching Pulse in Ferroelectric Lanthanum-doped HfO 2 with Large Single Grain of Orthorhombic Phase> 38 nm, in 2022 International Electron Devices Meeting (IEDM). IEEE; 2022:6–5.
Ma Y, Wu Z, Lu CQ. The relationship between job insecurity and employee information security behavior: An exploratory study, in The 2022 Academic Annual Meeting of the Managerial Psychology Professional Committee of the Chinese Association of Social Psychology (The 4th China Managerial Psychology/Organizational Behavior Forum). Kunming, China; 2022.
Chen X, Shen Q, Cheng P, Xiong Y, Wu Z. RuleCache: Accelerating Web Application Firewalls by On-line Learning Traffic Patterns, in IEEE International Conference on Web Services, ICWS 2022, Barcelona, Spain, July 10-16, 2022. IEEE; 2022:229–239. 访问链接
Liu J, Wang X-P, Xie K-P. Scalar-mediated dark matter model at colliders and gravitational wave detectors - A White paper for Snowmass 2021, in Snowmass 2021.; 2022.
Luo W, Ding X, Wu P, Zhang X, Shen Q, Wu Z. ScriptChecker: To Tame Third-party Script Execution With Task Capabilities, in 29th Annual Network and Distributed System Security Symposium, NDSS 2022, San Diego, California, USA, April 24-28, 2022. The Internet Society; 2022. 访问链接
Zhang Y, Xue C, Wang X, Liu T, Gao J, Chen P, Liu J, Sun L, Shen L, Ru J, et al. Single-Mode CMOS 6T-SRAM Macros With Keeper-Loading-Free Peripherals and Row-Separate Dynamic Body Bias Achieving 2.53fW/bit Leakage for AIoT Sensing Platforms, in 2022 IEEE International Solid- State Circuits Conference (ISSCC).Vol 65.; 2022:184-186.
Ding Z, Zhao R, Zhang J, Gao T, Xiong R, Yu Z*, Huang T. Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation, in Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI).; 2022.Abstract
Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing model-free solutions to many event-based problems, such as optical flow estimation. However, existing deep learning methods did not address the importance of temporal information well from the perspective of architecture design and cannot effectively extract spatio-temporal features. Another line of research that utilizes Spiking Neural Network suffers from training issues for deeper architecture. To address these points, a novel input representation is proposed that captures the events temporal distribution for signal enhancement. Moreover, we introduce a spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images. Besides, our architecture allows some traditional frame-based core modules, such as correlation layer and iterative residual refine scheme, to be incorporated. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin.
Wang Y. A SPICE-Based Simulation Method for System Efficient Electrostatic Discharge Design (invited talk), in 6th IEEE Electron Devices Technology and Manufacturing Conference (EDTM). Oita, Japan: IEEE Press; 2022.Abstract
Based on system efficient electrostatic discharge design (SEED) methodology, this paper proposes a high-order SPICE simulation methodology to predict the performance of the ESD protection circuits. The related PCB-level experiments of the selected protection circuits are fulfilled to verify this method. As a result, the consistency of the comparison results between the simulation and measurement illustrates that the method can accurately predict the performance of system-level protection circuits.
Zhao J, Zhang S*, Ma L*, Yu Z, Huang T. SpikingSIM: A Bio-Inspired Spiking Simulator, in IEEE International Symposium on Circuits and Systems (ISCAS).; 2022.Abstract
Large-scale neuromorphic dataset is costly to construct and difficult to annotate because of the unique high-speed asynchronous imaging principle of bio-inspired cameras. Lacking of large-scale annotated neuromorphic datasets has significantly hindered the applications of bio-inspired cameras in deep neural networks. Synthesizing neuromorphic data from annotated RGB images can be considered to alleviate this challenge. This paper proposes a simulator to generate simulated spiking data from images recorded by frame cameras. To minimize the deviationsbetween synthetic data and real data, the proposed simulator named SpikingSIM considers the sensing principle of spiking cameras, and generates high-quality simulated spiking data, e.g., the noises in real data are also simulated. Experimental results show that, our simulator generates more realistic spiking data than existing methods. We hence train deep neural networks with synthesized spiking data. Experiments show that, the network trained by our simulated data generalizes well on real spiking data. The source code of SpikingSIM is available at http://github.com/Evin-X/SpikingSIM.
Xiong X, Liu S, Liu H, Chen Y, Shi X, Wang X, Li X, HUANG R, Wu Y. Top-Gate CVD WSe 2 pFETs with Record-High I d\~ 594 $μ$A/$μ$m, G m\~ 244 $μ$S/$μ$m and WSe 2/MoS 2 CFET based Half-adder Circuit Using Monolithic 3D Integration, in 2022 International Electron Devices Meeting (IEDM). IEEE; 2022:20–6.

Pages