Author name cluster

Shukai Duan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2025 Conference Paper

GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration

Yihao
Limei Hu
Feng Chen
Sen Zhao
Shukai Duan

The Iterative Closest Point (ICP) algorithm suffers from sensitivity to outliers and tendency to local optima in point cloud fine registration. In this paper, we introduce a global and robust ICP framework called Granular-Ball Iterative Closest Point with MultiKernel Correntropy (GRICP). This approach transforms the point cloud into a granular ball cloud and employs MultiKernel Correntropy (MKC) as the loss function, which is designed to smooth out the effects of noise points and provide global information for registration. Specifically, we propose a coarse-grained representation of the point cloud using the granular ball model, which adaptively captures the coarse-grained features of the data and converts the point cloud into a multi-granularity ball cloud. The normal points within each granular ball help mitigate the influence of noise points. To ensure that ICP finds the globally optimal transformation, MKC is introduced to measure the distribution of registration errors, thereby offering global insights for ICP to achieve the optimal solution. The transformations based on MKC and the granular ball cloud are then derived. Extensive experiments on both simulated and real-world datasets demonstrate that GRICP delivers superior registration performance, particularly in scenarios involving large rotation offsets, partial overlaps, and Gaussian noise.

PDF Details DOI

EAAI Journal 2025 Journal Article

Signal-to-noise ratio guided noise adaptive network via Dual-domain collaboration for low-light image enhancement

Yifei Wang
Chunyan She
Jie Sun
Shukai Duan
Lidan Wang

Low-light image enhancement is crucial for accurate perception and decision-making, particularly in fields like autonomous driving. However, noise is inherently present in low-light images, especially in extremely dark regions, which complicates the reconstruction of clear images. Transformer, which typically computes self-attention scores across all available tokens, often struggle with the interference caused by this noise. To address this challenge, we propose the Signal-to-Noise Ratio (SNR) guided Noise Adaptive Network (SNA-Net), a novel approach that leverages the strengths of both Convolutional Neural Networks (CNN) and Transformer to adapt to noise distribution across different regions for low-light image enhancement. The SNA-Net introduces two key components within the transformer block: Noise Adaptive Self-Attention (NASA) and Dual-domain Refinement Feed-forward Network (DRFN) Specifically, NASA adaptively computes attention scores using both dense and sparse branches. The sparse branch filters out negative token interactions in low SNR regions, while the dense branch preserves essential image information. In parallel, DRFN reduces feature redundancy in both the spatial and frequency domains, thereby improving the recovery of the underlying clear image. Additionally, to facilitate better integration between CNN and Transformer features, we design an SNR-guided Feature Fusion Module (SGFF). We validate the superior performance of SNA-Net on six datasets through extensive experiments. Our code is available at https: //github. com/Wyyff993/SNA-NET.

Details DOI

EAAI Journal 2025 Journal Article

Spatio-Temporal Channel Attention and Membrane Potential Modulation for Efficient Spiking neural network

Xingming Tang
Tao Chen
Qian Cheng
Hangchi Shen
Shukai Duan
Lidan Wang

Spiking Neural Networks (SNNs) are an energy-efficient alternative to Artificial Neural Networks (ANNs) due to their event-driven nature. However, common coding methods such as direct coding struggle to capture critical spatio-temporal dynamics. To address this, we propose a Spatio-Temporal Channel Attention (STCA) module to improve feature extraction during spike encoding. In addition, we introduce a Membrane Potential Modulator (MPM) to reduce information loss due to binary quantization. Together, STCA and MPM form the Gated Attention Coding Mechanism (GACM), which improves SNN training on both static and neuromorphic datasets. Experiments at the Canadian Institute for Advanced Research 10/100 (CIFAR10/100) and CIFAR10-Dynamic Vision Sensor (DVS) show that GACM has higher accuracy and significant efficiency over direct coding. In particular, we improved accuracy by 1. 73% on the CIFAR100 and 0. 81% on the CIFAR10 in fewer steps.

Details DOI

EAAI Journal 2024 Journal Article

A multilevel interleaved group attention-based convolutional network for gas detection via an electronic nose system

Shichao Zhai
Zhe Li
Huisheng Zhang
Lidan Wang
Shukai Duan
Jia Yan

In this paper, an E-nose system for industrial exhaust detection is established and a novel deep learning model called the multilevel interleaved group attention-based convolutional network (MIGACN) is proposed for processing sensor array signals to identify 10 kinds of industrial pollution gases. First, a homemade E-nose system consisting of 15 gas sensors was constructed to acquire industrial pollution gas samples. Second, for sensor array signal processing, two novel feature learning modules are proposed at both the temporal level and the sensor level based on the actual physical significance of the sensor signals to enable the network to automatically extract intrinsic features of the sensor response signals. Third, we introduce a data augmentation module to avoid the problem of insufficient model training due to limited data volume and achieve dynamic gas detection through sliding windows. The proposed MIGACN directly uses the original response of the sensors as the input to automatically extract the intrinsic signal features without tedious manual empirical feature extraction. The experimental results show that the MIGACN achieves better classification performance and excellent stability than do other advanced deep learning methods. MIGACN obtains 90. 76% classification accuracy without the data augmentation module. With the data augmentation module, the MIGACN obtains a testing accuracy of 98. 06% from the early sensor response stage. In addition, the MIGACN achieves the highest average dynamic detection accuracy of 98. 19% with the data augmentation module, which highlights its advantages in practical applications.

Details DOI

NeurIPS Conference 2024 Conference Paper

A Structure-Aware Framework for Learning Device Placements on Computation Graphs

Shukai Duan
Heng Ping
Nikos Kanakaris
Xiongye Xiao
Panagiotis Kyriakis
Nesreen K. Ahmed
Peiyu Zhang
Guixiang Ma

Computation graphs are Directed Acyclic Graphs (DAGs) where the nodes correspond to mathematical operations and are used widely as abstractions in optimizations of neural networks. The device placement problem aims to identify optimal allocations of those nodes to a set of (potentially heterogeneous) devices. Existing approaches rely on two types of architectures known as grouper-placer and encoder-placer, respectively. In this work, we bridge the gap between encoder-placer and grouper-placer techniques and propose a novel framework for the task of device placement, relying on smaller computation graphs extracted from the OpenVINO toolkit. The framework consists of five steps, including graph coarsening, node representation learning and policy optimization. It facilitates end-to-end training and takes into account the DAG nature of the computation graphs. We also propose a model variant, inspired by graph parsing networks and complex network analysis, enabling graph representation learning and jointed, personalized graph partitioning, using an unspecified number of groups. To train the entire framework, we use reinforcement learning using the execution time of the placement as a reward. We demonstrate the flexibility and effectiveness of our approach through multiple experiments with three benchmark models, namely Inception-V3, ResNet, and BERT. The robustness of the proposed framework is also highlighted through an ablation study. The suggested placements improve the inference speed for the benchmark models by up to $58. 2\%$ over CPU execution and by up to $60. 24\%$ compared to other commonly used baselines.

PDF Details DOI