Author name cluster

Qing Xu

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.

6 papers

1 author row

EAAI Journal 2026 Journal Article

Dynamic heuristic phased Double Deep Q Network path planning algorithm based on Gaussian mixture regression in discrete traffic environment

Ruixin Zhang
Qing Xu
Kai Sun
Zhilin He
Yi Liu
Youneng Su
Jingyi Wang
Xinming Zhu

In outdoor path planning, effectively balancing the relationship between path capacity and path length remains a significant challenge in current research. To address this challenge, we propose a phased DDQN (Double Deep Q Network) path planning algorithm that integrates Gaussian mixture regression and dynamic heuristics within a discrete traffic environment: GMR-DDQN (Double deep Q network with Gaussian mixture regression). First, the influence of land cover and terrain on vehicle capacity is considered, leading to the formulation of a reward function and the development of a multi-coupled discrete toll cost model. Next, toll costs are incorporated into the DDQN using a greedy strategy, while heuristic methods are applied to generate multiple demonstration trajectories with minimal training. Then, Gaussian mixture regression is employed to gather demonstration trajectory data, construct the proposed path, and generate a buffer-constrained sampling area. The model is further trained to refine the trajectories. Finally, the performance of the algorithm is evaluated in three different traffic environments. Experimental results indicate that, compared to the improved DQN (Deep Q Network) and DDQN algorithms, GMR-DDQN reduces code execution time by 50. 27 %–74. 93 %, shortens path passage time by 27. 12 %–37. 29 %, decreases the average number of steps by 78. 12 %–88. 33 %, and increases the average reward by at least 18, 000 points. Additionally, compared to the unconstrained GMR-DDQN, GMR-DDQN cuts code running time by 25. 79 %–50. 27 %. The results demonstrate that GMR-DDQN can efficiently utilize the road network to enhance traffic efficiency.

Details DOI

YNIMG Journal 2024 Journal Article

A method to image brain tissue frozen at autopsy

Govind Nair
Roy Sun
Hellmut Merkle
Qing Xu
Kyra Hoskin
Kendyl Bree
Stephen Dodd
Alan P. Koretsky

Magnetic Resonance Imaging (MRI) can provide the location and signal characteristics of pathological regions within a postmortem tissue block, thereby improving the efficiency of histopathological studies. However, such postmortem-MRI guided histopathological studies have so far only been performed on fixed samples as imaging tissue frozen at the time of extraction, while preserving its integrity, is significantly more challenging. Here we describe the development of cold-postmortem-MRI, which can preserve tissue integrity and help target techniques such as transcriptomics. As a first step, RNA integrity number (RIN) was used to determine the rate of tissue biomolecular degradation in mouse brains placed at various temperatures between -20 °C and +20 °C for up to 24 h. Then, human tissue frozen at the time of autopsy was immersed in 2-methylbutane, sealed in a bio-safe tissue chamber, and cooled in the MRI using a recirculating chiller to determine MRI signal characteristics. The optimal imaging temperature, which did not show significant RIN deterioration for over 12 h, at the same time giving robust MRI signal and contrast between brain tissue types was deemed to be -7 °C. Finally, MRI was performed on human tissue blocks at this optimal imaging temperatures using a magnetization-prepared rapid gradient echo (MPRAGE, isotropic resolution between 0.3-0.4 mm) revealing good gray-white matter contrast and revealing subpial, subcortical, and deep white matter lesions. RINs measured before and after imaging revealed no significant changes (n = 3, p = 0.18, paired t-test). In addition to improving efficiency of downstream processes, imaging tissue at sub-zero temperatures may also improve our understanding of compartment specificity of MRI signal.

Details DOI

NeurIPS Conference 2024 Conference Paper

Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM

Chenxin Li
Yuzhi Huang
Wuyang Li
Hengyu Liu
Xinyu Liu
Qing Xu
Zhen Chen
Yue Huang

As the vision foundation models like the Segment Anything Model (SAM) demonstrate potent universality, they also present challenges in giving ambiguous and uncertain predictions. Significant variations in the model output and granularity can occur with simply subtle changes in the prompt, contradicting the consensus requirement for the robustness of a model. While some established works have been dedicated to stabilizing and fortifying the prediction of SAM, this paper takes a unique path to explore how this flaw can be inverted into an advantage when modeling inherently ambiguous data distributions. We introduce an optimization framework based on a conditional variational autoencoder, which jointly models the prompt and the granularity of the object with a latent probability distribution. This approach enables the model to adaptively perceive and represent the real ambiguous label distribution, taming SAM to produce a series of diverse, convincing, and reasonable segmentation outputs controllably. Extensive experiments on several practical deployment scenarios involving ambiguity demonstrates the exceptional performance of our framework. Project page: \url{https: //a-sa-m. github. io/}.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Reinforced Cross-Domain Knowledge Distillation on Time Series Data

Qing Xu
Min Wu
Xiaoli Li
Kezhi Mao
Zhenghua Chen

Unsupervised domain adaptation methods have demonstrated superior capabilities in handling the domain shift issue which widely exists in various time series tasks. However, their prominent adaptation performances heavily rely on complex model architectures, posing an unprecedented challenge in deploying them on resource-limited devices for real-time monitoring. Existing approaches, which integrates knowledge distillation into domain adaptation frameworks to simultaneously address domain shift and model complexity, often neglect network capacity gap between teacher and student and just coarsely align their outputs over all source and target samples, resulting in poor distillation efficiency. Thus, in this paper, we propose an innovative framework named Reinforced Cross-Domain Knowledge Distillation (RCD-KD) which can effectively adapt to student's network capability via dynamically selecting suitable target domain samples for knowledge transferring. Particularly, a reinforcement learning-based module with a novel reward function is proposed to learn optimal target sample selection policy based on student's capacity. Meanwhile, a domain discriminator is designed to transfer the domain invariant knowledge. Empirical experimental results and analyses on four public time series datasets demonstrate the effectiveness of our proposed method over other state-of-the-art benchmarks.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data

Qing Xu
Min Wu
Xiaoli Li
Kezhi Mao
Zhenghua Chen

For many real-world time series tasks, the computational complexity of prevalent deep leaning models often hinders the deployment on resource limited environments (e. g. , smartphones). Moreover, due to the inevitable domain shift between model training (source) and deploying (target) stages, compressing those deep models under cross-domain scenarios becomes more challenging. Although some of existing works have already explored cross-domain knowledge distillation for model compression, they are either biased to source data or heavily tangled between source and target data. To this end, we design a novel end-to-end framework called UNiversal and joInt Knowledge Distillation (UNI-KD) for cross-domain model compression. In particular, we propose to transfer both the universal feature-level knowledge across source and target domains and the joint logit-level knowledge shared by both domains from the teacher to the student model via an adversarial learning scheme. More specifically, a feature-domain discriminator is employed to align teacher’s and student’s representations for universal knowledge transfer. A data-domain discriminator is utilized to prioritize the domain-shared samples for joint knowledge transfer. Extensive experimental results on four time series datasets demonstrate the superiority of our proposed method over state-of-the-art (SOTA) benchmarks. The source code is available at https: //github. com/ijcai2023/UNI KD.

PDF Details DOI

YNIMG Journal 2011 Journal Article

Empathic responses to others’ gains and losses: An electrophysiological investigation

Qingguo Ma
Qiang Shen
Qing Xu
Diandian Li
Liangchao Shu
Bernd Weber

A growing number of studies in exploring empathic modulation have revealed the neural substrates of how social stimuli are represented in the human brain, especially the pain of others. The empathic response of observing other's gains and losses, however, remains not clearly characterized. In the current study, we carried out two experiments with a gamble task to investigate how the effects of interpersonal familiarity and self-participation work on modulating the temporal neural response towards gain and loss of a friend or a stranger using scalp-recorded event-related potentials (ERPs). The electrophysiological data show an increased amplitude of the P300 when observing a friend's performance compared to strangers playing the game in both two experiments. But the distinction of differentiated feedback-related negativity (d-FRN) between friends and strangers was only observed when the player was not involved in the game. These results indicated that the participants exerted more motivational relevance toward their friends than strangers, but the participants’ empathic response toward friends was only salient when they were not involved in the gamble directly. Therefore, both familiarity and self-engagement are factors that influence the empathy towards others, complementing the recent research on empathic modulation.

Details DOI