Author name cluster

Hong Qu

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.

7 papers

2 author rows

AAAI Conference 2025 Conference Paper

HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions

Keyu Du
Hao Xu
Haipeng Li
Hong Qu
Chi-Wing Fu
Shuaicheng Liu

Scene-level point cloud registration is very challenging when considering dynamic foregrounds. Existing indoor datasets mostly assume rigid motions, so the trained models cannot robustly handle scenes with non-rigid motions. On the other hand, non-rigid datasets are mainly object-level, so the trained models cannot generalize well to complex scenes. This paper presents HybridReg, a new approach to 3D point cloud registration, learning uncertainty mask to account for hybrid motions: rigid for backgrounds and non-rigid/rigid for instance-level foregrounds. First, we build a scene-level 3D registration dataset, namely HybridMatch, designed specifically with strategies to arrange diverse deforming foregrounds in a controllable manner. Second, we account for different motion types and formulate a mask-learning module to alleviate the interference of deforming outliers. Third, we exploit a simple yet effective negative log-likelihood loss to adopt uncertainty to guide the feature extraction and correlation computation. To our best knowledge, HybridReg is the first work that exploits hybrid motions for robust point cloud registration. Extensive experiments show HybridReg's strengths, leading it to achieve state-of-the-art performance on both widely-used indoor and outdoor datasets.

PDF Details DOI

ECAI Conference 2024 Conference Paper

Reasonable Gradients for Online Training Algorithms in Spiking Neural Networks

Lang Xue
Hanwen Liu
Jing Wang
Hong Qu

Spiking neural networks (SNNs) have the potential to simulate sparse and spatio-temporal dynamics observed in biological neurons, making them promising for achieving energy-efficient artificial general intelligence. While backpropagation through time (BPTT) ensures reliable precision for training SNNs, it is hampered by high computation and storage complexity and does not conform to the instantaneous learning mechanism in brains. On the contrary, online training algorithms, which are biologically interpretable, offer low latency and memory efficiency, and are well-suited for on-chip learning applications. However, recent research exhibit a deficiency in the scientific comprehension of online gradients, which leads to certain limitations. To address this issue, we conduct an in-depth analysis of the calculation deviation in chain derivations induced by weight update and find two pivotal factors that affect the accuracy of online gradients: completeness and timeliness. To further enhance the performance of online training leveraging these findings, we propose spatio-temporal online learning (STOL), which substantially ameliorates the accuracy of the online gradients and demonstrates superior computation and memory efficiency. Our experiments on CIFAR-10, CIFAR-100, ImageNet, CIFAR10-DVS, and DVS128-Gesture datasets demonstrate that our method achieves state-of-the-art performance across most of these tasks. Besides, it shows a great improvement compared with existing online training algorithms.

Details

IJCAI Conference 2023 Conference Paper

Spatial-Temporal Self-Attention for Asynchronous Spiking Neural Networks

Yuchen Wang
Kexin Shi
Chengzhuo Lu
Yuguo Liu
Malu Zhang
Hong Qu

The brain-inspired spiking neural networks (SNNs) are receiving increasing attention due to their asynchronous event-driven characteristics and low power consumption. As attention mechanisms recently become an indispensable part of sequence dependence modeling, the combination of SNNs and attention mechanisms holds great potential for energy-efficient and high-performance computing paradigms. However, the existing works cannot benefit from both temporal-wise attention and the asynchronous characteristic of SNNs. To fully leverage the advantages of both SNNs and attention mechanisms, we propose an SNNs-based spatial-temporal self-attention (STSA) mechanism, which calculates the feature dependence across the time and space domains without destroying the asynchronous transmission properties of SNNs. To further improve the performance, we also propose a spatial-temporal relative position bias (STRPB) for STSA to consider the spatiotemporal position of spikes. Based on the STSA and STRPB, we construct a spatial-temporal spiking Transformer framework, named STS-Transformer, which is powerful and enables SNNs to work in an asynchronous event-driven manner. Extensive experiments are conducted on popular neuromorphic datasets and speech datasets, including DVS128 Gesture, CIFAR10-DVS, and Google Speech Commands, and our experimental results can outperform other state-of-the-art models.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Substructure Aware Graph Neural Networks

DingYi Zeng
Wanlong Liu
Wenyu Chen
Li Zhou
Malu Zhang
Hong Qu

Despite the great achievements of Graph Neural Networks (GNNs) in graph learning, conventional GNNs struggle to break through the upper limit of the expressiveness of first-order Weisfeiler-Leman graph isomorphism test algorithm (1-WL) due to the consistency of the propagation paradigm of GNNs with the 1-WL.Based on the fact that it is easier to distinguish the original graph through subgraphs, we propose a novel framework neural network framework called Substructure Aware Graph Neural Networks (SAGNN) to address these issues. We first propose a Cut subgraph which can be obtained from the original graph by continuously and selectively removing edges. Then we extend the random walk encoding paradigm to the return probability of the rooted node on the subgraph to capture the structural information and use it as a node feature to improve the expressiveness of GNNs. We theoretically prove that our framework is more powerful than 1-WL, and is superior in structure perception. Our extensive experiments demonstrate the effectiveness of our framework, achieving state-of-the-art performance on a variety of well-proven graph tasks, and GNNs equipped with our framework perform flawlessly even in 3-WL failed graphs. Specifically, our framework achieves a maximum performance improvement of 83% compared to the base models and 32% compared to the previous state-of-the-art methods.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Signed Neuron with Memory: Towards Simple, Accurate and High-Efficient ANN-SNN Conversion

Yuchen Wang
Malu Zhang
Yi Chen
Hong Qu

Spiking Neural Networks (SNNs) are receiving increasing attention due to their biological plausibility and the potential for ultra-low-power event-driven neuromorphic hardware implementation. Due to the complex temporal dynamics and discontinuity of spikes, training SNNs directly usually suffers from high computing resources and a long training time. As an alternative, SNN can be converted from a pre-trained artificial neural network (ANN) to bypass the difficulty in SNNs learning. However, the existing ANN-to-SNN methods neglect the inconsistency of information transmission between synchronous ANNs and asynchronous SNNs. In this work, we first analyze how the asynchronous spikes in SNNs may cause conversion errors between ANN and SNN. To address this problem, we propose a signed neuron with memory function, which enables almost no accuracy loss during the conversion process, and maintains the properties of asynchronous transmission in the converted SNNs. We further propose a new normalization method, named neuron-wise normalization, to significantly shorten the inference latency in the converted SNNs. We conduct experiments on challenging datasets including CIFAR10 (95. 44% top-1), CIFAR100 (78. 3% top-1) and ImageNet (73. 16% top-1). Experimental results demonstrate that the proposed method outperforms the state-of-the-art works in terms of accuracy and inference time. The code is available at https: //github. com/ppppps/ANN2SNNConversion_SNM_NeuronNorm.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Deep Spiking Neural Network with Neural Oscillation and Spike-Phase Information

Yi Chen
Hong Qu
Malu Zhang
Yuchen Wang

Deep spiking neural network (DSNN) is a promising computational model towards artificial intelligence. It benefits from both the DNNs and SNNs through a hierarchy structure to extract multiple levels of abstraction and the event-driven computational manner to provide ultra-low-power neuromorphic implementation, respectively. However, how to efficiently train the DSNNs remains an open question because of the non-differentiable spike function that prevents the traditional back-propagation (BP) learning algorithm directly applied to DSNNs. Here, inspired by the findings from the biological neural networks, we address the above-mentioned problem by introducing neural oscillation and spike-phase information to DSNNs. Specifically, we propose an Oscillation Postsynaptic Potential (Os-PSP) and phase-locking active function, and further put forward a new spiking neuron model, namely Resonate Spiking Neuron (RSN). Based on the RSN, we propose a Spike-Level-Dependent Back-Propagation (SLDBP) learning algorithm for DSNNs. Experimental results show that the proposed learning algorithm resolves the problems caused by the incompatibility between the BP learning algorithm and SNNs, and achieves state-of-the-art performance in single spike-based learning algorithms. This work investigates the contribution of introducing biologically inspired mechanisms, such as neural oscillation and spike-phase information to DSNNs and providing a new perspective to design future DSNNs.

PDF Details

YNIMG Journal 2007 Journal Article

In vivo mapping of temporospatial changes in manganese enhancement in rat brain during epileptogenesis

Silje Alvestad
Pål Erik Goa
Hong Qu
Øystein Risa
Christian Brekken
Ursula Sonnewald
Olav Haraldseth
Janniche Hammer

Mesial temporal lobe epilepsy is associated with structural and functional abnormalities, such as hippocampal sclerosis and axonal reorganization. The temporal evolution of these changes remains to be determined, and there is a need for in vivo imaging techniques that can uncover the epileptogenic processes at an early stage. Manganese-enhanced magnetic resonance imaging may be useful in this regard. The aim of this study was to analyze the temporospatial changes in manganese enhancement in rat brain during the development of epilepsy subsequent to systemic kainate application (10 mg/kg i. p.). MnCl2 was given systemically on day 2 (early), day 15 (latent), and 11 weeks (chronic phase) after the initial status epilepticus. Twenty-four hours after MnCl2 injection T1-weighted 3D MRI was performed followed by analysis of manganese enhancement. In the medial temporal lobes, there was a pronounced decrease in manganese enhancement in CA1, CA3, dentate gyrus, entorhinal cortex and lateral amygdala in the early phase. In the latent and chronic phases, recovery of the manganese enhancement was observed in all these structures except CA1. A significant increase in manganese enhancement was detected in the entorhinal cortex and the amygdala in the chronic phase. In the latter phase, the structurally intact cerebellum showed significantly decreased manganese enhancement. The highly differentiated changes in manganese enhancement are likely to represent the net outcome of a number of pathological and pathophysiological events, including cell loss and changes in neuronal activity. Our findings are not consistent with the idea that manganese enhancement primarily reflects changes in glial cells.

Details DOI