Search Results for author: Qi Xu

Found 26 papers, 4 papers with code

Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future

1 code implementation8 Oct 2024 Long Chen, Yuzhi Huang, Junyu Dong, Qi Xu, Sam Kwong, Huimin Lu, Huchuan Lu, Chongyi Li

In this survey, we first categorise existing algorithms into traditional machine learning-based methods and deep learning-based methods, and summarise them by considering learning strategy, experimental dataset, utilised features or frameworks, and learning stage.

object-detection Object Detection

Ads Supply Personalization via Doubly Robust Learning

no code implementations29 Sep 2024 Wei Shi, Chen Fu, Qi Xu, Sanjian Chen, Jizhe Zhang, Qinqin Zhu, Zhigang Hua, Shuang Yang

In the industry-scale system, the challenge for ads supply lies in modeling the counterfactual effects of a conservative supply treatment (e. g., a small density change) over an extended duration.

counterfactual

Allium Vegetables Intake and Digestive System Cancer Risk: A Study Based on Mendelian Randomization, Network Pharmacology and Molecular Docking

no code implementations16 Sep 2024 Shuhao Li, Jingwen Lou, Yelina Mulatihan, Yuhang Xiong, Yao Li, Qi Xu

Therefore, we explored the causal relationship between intake of allium vegetables and digestive system cancers using Mendelian randomization approach.

Molecular Docking

Context Gating in Spiking Neural Networks: Achieving Lifelong Learning through Integration of Local and Global Plasticity

no code implementations4 Jun 2024 Jiangrong Shen, Wenyao Ni, Qi Xu, Gang Pan, Huajin Tang

Inspired by biological context-dependent gating mechanisms found in PFC, we propose SNN with context gating trained by the local plasticity rule (CG-SNN) for lifelong learning.

Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning

no code implementations3 Jun 2024 Yaxin Li, Qi Xu, Jiangrong Shen, Hongming Xu, Long Chen, Gang Pan

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant structural units, aiming to more effectively leverage their low-power consumption and biological interpretability advantages.

Model Compression Network Pruning +1

QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models

no code implementations14 May 2024 Wei Wang, Zhaowei Li, Qi Xu, Yiqing Cai, Hang Song, Qi Qi, Ran Zhou, Zhida Huang, Tao Wang, Li Xiao

For negative knowledge, we propose an innovative self-adversarial approach that generates low-quality rationales by sampling previous iterations of smaller language models, embracing the idea that one can learn from one's own weaknesses.

Contrastive Learning Denoising +3

Defending Spiking Neural Networks against Adversarial Attacks through Image Purification

no code implementations26 Apr 2024 Weiran Chen, Qi Sun, Qi Xu

Spiking Neural Networks (SNNs) aim to bridge the gap between neuroscience and machine learning by emulating the structure of the human nervous system.

Denoising

Tunable Superconducting Magnetic Levitation with Self-Stability

no code implementations28 Mar 2024 Qi Xu, Yi Lin, Yunfei Tan, Jianzhao Geng

For the first time, we experimentally demonstrate a self-stable type II superconducting maglev system which is able to: counteract long term levitation force decay, adjust levitation force and equilibrium position, and establish levitation under zero field cooling condition.

DragTex: Generative Point-Based Texture Editing on 3D Mesh

no code implementations4 Mar 2024 Yudi Zhang, Qi Xu, Lei Zhang

Creating 3D textured meshes using generative artificial intelligence has garnered significant attention recently.

Decoder Texture Synthesis

Localization of Dummy Data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach

no code implementations27 Jan 2024 Zhaoyang Qu, Yunchang Dong, Yang Li, Siqi Song, Tao Jiang, Min Li, Qiming Wang, Lei Wang, Xiaoyong Bo, Jiye Zang, Qi Xu

Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization.

GroundingGPT:Language Enhanced Multi-modal Grounding Model

2 code implementations11 Jan 2024 Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, Yiqing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Van Tu Vu, Zhida Huang, Tao Wang

Beyond capturing global information like other multi-modal models, our proposed model excels at tasks demanding a detailed understanding of local information within the input.

Language Modelling Large Language Model

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks

no code implementations NeurIPS 2023 Qi Xu, Yuyuan Gao, Jiangrong Shen, Yaxin Li, Xuming Ran, Huajin Tang, Gang Pan

Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from Dynamic Vision Sensor (DVS).

Time Series

Graph Attention-Based Symmetry Constraint Extraction for Analog Circuits

1 code implementation22 Dec 2023 Qi Xu, Lijie Wang, Jing Wang, Lin Cheng, Song Chen, Yi Kang

In recent years, analog circuits have received extensive attention and are widely used in many emerging applications.

Graph Attention

Individualized Dynamic Latent Factor Model for Multi-resolutional Data with Application to Mobile Health

no code implementations21 Nov 2023 Jiuchen Zhang, Fei Xue, Qi Xu, Jung-Ah Lee, Annie Qu

In this paper, we propose an individualized dynamic latent factor model for irregular multi-resolution time series data to interpolate unsampled measurements of time series with low resolution.

Irregular Time Series Time Series

ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks

no code implementations6 Jun 2023 Jiangrong Shen, Qi Xu, Jian K. Liu, Yueming Wang, Gang Pan, Huajin Tang

To take full advantage of low power consumption and improve the efficiency of these models further, the pruning methods have been explored to find sparse SNNs without redundancy connections after training.

NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators with 3D-Stacked-DRAM

no code implementations30 May 2023 Junpeng Wang, Mengke Ge, Bo Ding, Qi Xu, Song Chen, Yi Kang

As one of the feasible processing-in-memory(PIM) architectures, 3D-stacked-DRAM-based PIM(DRAM-PIM) architecture enables large-capacity memory and low-cost memory access, which is a promising solution for DNN accelerators with better performance and energy efficiency.

Scheduling

Difference-in-Differences with Compositional Changes

no code implementations27 Apr 2023 Pedro H. C. Sant'Anna, Qi Xu

Additionally, we document a trade-off related to compositional changes: We derive the asymptotic bias of DR DiD estimators that erroneously exclude compositional changes and the efficiency loss when one fails to correctly rule out compositional changes.

Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks

no code implementations19 Apr 2023 Qi Xu, Yaxin Li, Xuanye Fang, Jiangrong Shen, Jian K. Liu, Huajin Tang, Gang Pan

The proposed method explores a novel dynamical way for structure learning from scratch in SNNs which could build a bridge to close the gap between deep learning and bio-inspired neural dynamics.

Knowledge Distillation

Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation

no code implementations CVPR 2023 Qi Xu, Yaxin Li, Jiangrong Shen, Jian K Liu, Huajin Tang, Gang Pan

Spiking neural networks (SNNs) are well known as the brain-inspired models with high computing efficiency, due to a key component that they utilize spikes as information units, close to the biological neural systems.

Knowledge Distillation

Task modules Partitioning, Scheduling and Floorplanning for Partially Dynamically Reconfigurable Systems Based on Modern Heterogeneous FPGAs

no code implementations11 Dec 2022 Bo Ding, Jinglei Huang, Junpeng Wang, Qi Xu, Song Chen, Yi Kang

To better solve the problems in the automation process of FPGA-PDRS and narrow the gap between algorithm and application, in this paper, we propose a complete workflow including three parts, pre-processing to generate the list of task modules candidate shapes according to the resources requirements, exploration process to search the solution of task modules partitioning, scheduling, and floorplanning, and post-optimization to improve the success rate of floorplan.

Scheduling

Deep Auto-encoder with Neural Response

no code implementations30 Nov 2021 Xuming Ran, Jie Zhang, Ziyuan Ye, Haiyan Wu, Qi Xu, Huihui Zhou, Quanying Liu

In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons.

Decoder Image Reconstruction

Two Sample Unconditional Quantile Effect

no code implementations20 May 2021 Atsushi Inoue, Tong Li, Qi Xu

This paper proposes a new framework to evaluate unconditional quantile effects (UQE) in a data combination model.

counterfactual Vocal Bursts Valence Prediction

Bigeminal Priors Variational auto-encoder

no code implementations5 Oct 2020 Xuming Ran, Mingkun Xu, Qi Xu, Huihui Zhou, Quanying Liu

The likelihood-based generative models have been reported to be highly robust to the out-of-distribution (OOD) inputs and can be a detector by assuming that the model assigns higher likelihoods to the samples from the in-distribution (ID) dataset than an OOD dataset.

Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation

no code implementations16 Jul 2020 Xuming Ran, Mingkun Xu, Lingrui Mei, Qi Xu, Quanying Liu

To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs.

Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.