arXiv subjects

Zhicheng Zhang

Publications and source records attributed to Zhicheng Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2024

Unlocking the Potential of Early Epochs: Uncertainty-aware CT Metal Artifact Reduction

In computed tomography (CT), the presence of metallic implants in patients often leads to disruptive artifacts in the reconstructed images, hindering accurate diagnosis. Recently, a large amount of supervised deep learning-based approaches have been proposed for metal artifact reduction (MAR). However, these methods neglect the influence of initial training weights. In this paper, we have discovered that the uncertainty image computed from the restoration result of initial training weights can effectively highlight high-frequency regions, including metal artifacts. This observation can be leveraged to assist the MAR network in removing metal artifacts. Therefore, we propose an uncertainty constraint (UC) loss that utilizes the uncertainty image as an adaptive weight to guide the MAR network to focus on the metal artifact region, leading to improved restoration. The proposed UC loss is designed to be a plug-and-play method, compatible with any MAR framework, and easily adoptable. To validate the effectiveness of the UC loss, we conduct extensive experiments on the public available Deeplesion and CLINIC-metal dataset. Experimental results demonstrate that the UC loss further optimizes the network training process and significantly improves the removal of metal artifacts.

eess.IV↗

arXiv2024

MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection

Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to generate multi-scale spectral and spatial features. The TF-Convolution Module is employed to provide multi-scale temporal features. We incorporated MFF into EINV2 and term the proposed method as MFF-EINV2. Experimental results in 2022 and 2023 DCASE challenge task3 datasets show the effectiveness of our MFF-EINV2, which achieves state-of-the-art (SOTA) performance compared to published methods.

cs.SD↗

arXiv2024

Micro-expression recognition based on depth map to point cloud

Micro-expressions are nonverbal facial expressions that reveal the covert emotions of individuals, making the micro-expression recognition task receive widespread attention. However, the micro-expression recognition task is challenging due to the subtle facial motion and brevity in duration. Many 2D image-based methods have been developed in recent years to recognize MEs effectively, but, these approaches are restricted by facial texture information and are susceptible to environmental factors, such as lighting. Conversely, depth information can effectively represent motion information related to facial structure changes and is not affected by lighting. Motion information derived from facial structures can describe motion features that pixel textures cannot delineate. We proposed a network for micro-expression recognition based on facial depth information, and our experiments have demonstrated the crucial role of depth maps in the micro-expression recognition task. Initially, we transform the depth map into a point cloud and obtain the motion information for each point by aligning the initiating frame with the apex frame and performing a differential operation. Subsequently, we adjusted all point cloud motion feature input dimensions and used them as inputs for multiple point cloud networks to assess the efficacy of this representation. PointNet++ was chosen as the ultimate outcome for micro-expression recognition due to its superior performance. Our experiments show that our proposed method significantly outperforms the existing deep learning methods, including the baseline, on the $CAS(ME)^3$ dataset, which includes depth information.

eess.IV↗

arXiv2024

New Quantum Algorithms for Computing Quantum Entropies and Distances

We propose a series of quantum algorithms for computing a wide range of quantum entropies and distances, including the von Neumann entropy, quantum Rényi entropy, trace distance, and fidelity. The proposed algorithms significantly outperform the prior best (and even quantum) ones in the low-rank case, some of which achieve exponential speedups. In particular, for $N$-dimensional quantum states of rank $r$, our proposed quantum algorithms for computing the von Neumann entropy, trace distance and fidelity within additive error $\varepsilon$ have time complexity of $\tilde O(r/\varepsilon^2)$, $\tilde O(r^5/\varepsilon^6)$ and $\tilde O(r^{6.5}/\varepsilon^{7.5})$, respectively. By contrast, prior quantum algorithms for the von Neumann entropy and trace distance usually have time complexity $Ω(N)$, and the prior best one for fidelity has time complexity $\tilde O(r^{12.5}/\varepsilon^{13.5})$. The key idea of our quantum algorithms is to extend block-encoding from unitary operators in previous work to quantum states (i.e., density operators). It is realized by developing several convenient techniques to manipulate quantum states and extract information from them. The advantage of our techniques over the existing methods is that no restrictions on density operators are required; in sharp contrast, the previous methods usually require a lower bound on the minimal non-zero eigenvalue of density operators.

quant-ph↗

arXiv2024

A Framework for Inference Inspired by Human Memory Mechanisms

How humans and machines make sense of current inputs for relation reasoning and question-answering while putting the perceived information into context of our past memories, has been a challenging conundrum in cognitive science and artificial intelligence. Inspired by human brain's memory system and cognitive architectures, we propose a PMI framework that consists of perception, memory and inference components. Notably, the memory module comprises working and long-term memory, with the latter endowed with a higher-order structure to retain extensive and complex relational knowledge and experience. Through a differentiable competitive write access, current perceptions update working memory, which is later merged with long-term memory via outer product associations, reducing information conflicts and averting memory overflow. In the inference module, relevant information is retrieved from two separate memory origins and associatively integrated to attain a more comprehensive and precise interpretation of current perceptions. We exploratively apply our PMI to improve prevailing Transformers and CNN models on question-answering tasks like bAbI-20k and Sort-of-CLEVR datasets, as well as detecting equilateral triangles, language modeling and image classification tasks, and in each case, our PMI enhancements consistently outshine their original counterparts significantly. Visualization analyses reveal that relational memory consolidation, along with the interaction and integration of information from diverse memory sources, substantially contributes to the model effectiveness on inference tasks.

cs.LG↗

arXiv2024

MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure

Multi-agent reinforcement learning (MARL) algorithms often struggle to find strategies close to Pareto optimal Nash Equilibrium, owing largely to the lack of efficient exploration. The problem is exacerbated in sparse-reward settings, caused by the larger variance exhibited in policy learning. This paper introduces MESA, a novel meta-exploration method for cooperative multi-agent learning. It learns to explore by first identifying the agents' high-rewarding joint state-action subspace from training tasks and then learning a set of diverse exploration policies to "cover" the subspace. These trained exploration policies can be integrated with any off-policy MARL algorithm for test-time tasks. We first showcase MESA's advantage in a multi-step matrix game. Furthermore, experiments show that with learned exploration policies, MESA achieves significantly better performance in sparse-reward tasks in several multi-agent particle environments and multi-agent MuJoCo environments, and exhibits the ability to generalize to more challenging tasks at test time.

cs.LG↗

arXiv2024

Atomicity in Distributed Quantum Computing

Atomicity is a ubiquitous assumption in distributed computing, under which actions are indivisible and appear sequential. In classical computing, this assumption has several theoretical and practical guarantees. In quantum computing, although atomicity is still commonly assumed, it has not been seriously studied, and a rigorous basis for it is missing. Classical results on atomicity do not directly carry over to distributed quantum computing, due to new challenges caused by quantum entanglement and the measurement problem from the underlying quantum mechanics. In this paper, we initiate the study of atomicity in distributed quantum computing. A formal model of (non-atomic) distributed quantum system is established. Based on the Dijkstra-Lamport condition, the system dynamics and observable dynamics of a distributed quantum system are defined, which correspond to the quantum state of and classically observable events in the system, respectively. Within this framework, we prove that local actions can be regarded as if they were atomic, up to the observable dynamics of the system.

quant-ph↗

arXiv2024

Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning

Ultrasound (US) has been widely used in daily clinical practice for screening internal organs and guiding interventions. However, due to the acoustic shadow cast by the subcutaneous rib cage, the US examination for thoracic application is still challenging. To fully cover and reconstruct the region of interest in US for diagnosis, an intercostal scanning path is necessary. To tackle this challenge, we present a reinforcement learning (RL) approach for planning scanning paths between ribs to monitor changes in lesions on internal organs, such as the liver and heart, which are covered by rib cages. Structured anatomical information of the human skeleton is crucial for planning these intercostal paths. To obtain such anatomical insight, an RL agent is trained in a virtual environment constructed using computational tomography (CT) templates with randomly initialized tumors of various shapes and locations. In addition, task-specific state representation and reward functions are introduced to ensure the convergence of the training process while minimizing the effects of acoustic attenuation and shadows during scanning. To validate the effectiveness of the proposed approach, experiments have been carried out on unseen CTs with randomly defined single or multiple scanning targets. The results demonstrate the efficiency of the proposed RL framework in planning non-shadowed US scanning trajectories in areas with limited acoustic access.

cs.RO↗

arXiv2024

Geometric Approach to Mirabolic Schur-Weyl Duality of Type A

We commence by constructing the mirabolic quantum Schur algebra, utilizing the convolution algebra defined on the variety of triples of two $n$-step partial flags and a vector. Subsequently, we employ a stabilization procedure to derive the mirabolic quantum $\mathfrak{gl}_n$. Then we present the geometric approach of the mirabolic Schur-Weyl duality of type $A$.

math.RT↗

arXiv2024

Physics-constrained Attack against Convolution-based Human Motion Prediction

Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.

cs.CV↗

arXiv2024

Parallel Quantum Algorithm for Hamiltonian Simulation

We study how parallelism can speed up quantum simulation. A parallel quantum algorithm is proposed for simulating the dynamics of a large class of Hamiltonians with good sparse structures, called uniform-structured Hamiltonians, including various Hamiltonians of practical interest like local Hamiltonians and Pauli sums. Given the oracle access to the target sparse Hamiltonian, in both query and gate complexity, the running time of our parallel quantum simulation algorithm measured by the quantum circuit depth has a doubly (poly-)logarithmic dependence $\operatorname{polylog}\log(1/ε)$ on the simulation precision $ε$. This presents an exponential improvement over the dependence $\operatorname{polylog}(1/ε)$ of previous optimal sparse Hamiltonian simulation algorithm without parallelism. To obtain this result, we introduce a novel notion of parallel quantum walk, based on Childs' quantum walk. The target evolution unitary is approximated by a truncated Taylor series, which is obtained by combining these quantum walks in a parallel way. A lower bound $Ω(\log \log (1/ε))$ is established, showing that the $ε$-dependence of the gate depth achieved in this work cannot be significantly improved. Our algorithm is applied to simulating three physical models: the Heisenberg model, the Sachdev-Ye-Kitaev model and a quantum chemistry model in second quantization. By explicitly calculating the gate complexity for implementing the oracles, we show that on all these models, the total gate depth of our algorithm has a $\operatorname{polylog}\log(1/ε)$ dependence in the parallel setting.

quant-ph↗

arXiv2023

BiHRNet: A Binary high-resolution network for Human Pose Estimation

Human Pose Estimation (HPE) plays a crucial role in computer vision applications. However, it is difficult to deploy state-of-the-art models on resouce-limited devices due to the high computational costs of the networks. In this work, a binary human pose estimator named BiHRNet(Binary HRNet) is proposed, whose weights and activations are expressed as $\pm$1. BiHRNet retains the keypoint extraction ability of HRNet, while using fewer computing resources by adapting binary neural network (BNN). In order to reduce the accuracy drop caused by network binarization, two categories of techniques are proposed in this work. For optimizing the training process for binary pose estimator, we propose a new loss function combining KL divergence loss with AWing loss, which makes the binary network obtain more comprehensive output distribution from its real-valued counterpart to reduce information loss caused by binarization. For designing more binarization-friendly structures, we propose a new information reconstruction bottleneck called IR Bottleneck to retain more information in the initial stage of the network. In addition, we also propose a multi-scale basic block called MS-Block for information retention. Our work has less computation cost with few precision drop. Experimental results demonstrate that BiHRNet achieves a PCKh of 87.9 on the MPII dataset, which outperforms all binary pose estimation networks. On the challenging of COCO dataset, the proposed method enables the binary neural network to achieve 70.8 mAP, which is better than most tested lightweight full-precision networks.

cs.CV↗

arXiv2023

Fast Quantum Algorithms for Trace Distance Estimation

In quantum information, trace distance is a basic metric of distinguishability between quantum states. However, there is no known efficient approach to estimate the value of trace distance in general. In this paper, we propose efficient quantum algorithms for estimating the trace distance within additive error $\varepsilon$ between mixed quantum states of rank $r$. Specifically, we first provide a quantum algorithm using $r \cdot \widetilde O(1/\varepsilon^2)$ queries to the quantum circuits that prepare the purifications of quantum states. Then, we modify this quantum algorithm to obtain another algorithm using $\widetilde O(r^2/\varepsilon^5)$ samples of quantum states, which can be applied to quantum state certification. These algorithms have query/sample complexities that are independent of the dimension $N$ of quantum states, and their time complexities only incur an extra $O(\log (N))$ factor. In addition, we show that the decision version of low-rank trace distance estimation is $\mathsf{BQP}$-complete.

quant-ph↗

arXiv2023

Quantum Recursive Programming with Quantum Case Statements

We introduce a novel scheme of quantum recursive programming, in which large unitary transformations, i.e. quantum gates, can be recursively defined using quantum case statements, which are quantum counterparts of conditionals and case statements extensively used in classical programming. A simple programming language for supporting this kind of quantum recursion is defined, and its semantics is formally described. A series of examples are presented to show that some quantum algorithms can be elegantly written as quantum recursive programs.

cs.PL↗

arXiv2023

ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models

Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further unleash the power of LLMs to accomplish complex tasks, there is a growing trend to build agent framework that equips LLMs, such as ChatGPT, with tool-use abilities to connect with massive external APIs. In this work, we introduce ModelScope-Agent, a general and customizable agent framework for real-world applications, based on open-source LLMs as controllers. It provides a user-friendly system library, with customizable engine design to support model training on multiple open-source LLMs, while also enabling seamless integration with both model APIs and common APIs in a unified way. To equip the LLMs with tool-use abilities, a comprehensive framework has been proposed spanning over tool-use data collection, tool retrieval, tool registration, memory control, customized model training, and evaluation for practical real-world applications. Finally, we showcase ModelScopeGPT, a real-world intelligent assistant of ModelScope Community based on the ModelScope-Agent framework, which is able to connect open-source LLMs with more than 1000 public AI models and localized community knowledge in ModelScope. The ModelScope-Agent library\footnote{https://github.com/modelscope/modelscope-agent} and online demo\footnote{https://modelscope.cn/studios/damo/ModelScopeGPT/summary} are now publicly available.

cs.CL↗

arXiv2023

Sparse Feedback Controller: From Open-loop Solution to Closed-loop Realization

In this paper, we explore the discrete time sparse feedback control for a linear invariant system, where the proposed optimal feedback controller enjoys input sparsity by using a dynamic linear compensator, i.e., the components of feedback control signal having the smallest possible nonzero values. The resulting augmented dynamics ensures closed-loop stability, which infers sparse feedback controller from open-loop solution to closed-loop realization. In particular, we show that the implemented sparse feedback (closed-loop) control solution is equivalent to the original sparse (open-loop) control solution under a specified basis. We then extend the dynamic compensator to a feedforward tracking control problem. Finally, numerical examples demonstrate the effectiveness of proposed control approach.

eess.SY↗

arXiv2023

Intelligent mode-locked NPR fiber laser based on laser speckle characteristics

Passively mode-locked fiber lasers based on nonlinear polarization rotation (NPR) have been widely used due to their ability to produce short pulses with high peak power and broad spectrum. Nevertheless, environmental disturbances can disrupt the mode-locked state, making it a challenge for practical implementation. Therefore, scientists have proposed mode-locked NPR lasers assisted with artificial intelligence, which can effectively address the issues related to mode-locking stability. Speckle patterns containing spectral information can be generated when the laser transmitting through a scattering medium, which can be served as indicators of the mode-locked state. The contrast of the Tamura texture feature of the speckle patterns exhibits periodic "V" shaped variations with respect to the rotation angles of the waveplates, according to experimental results. The stable mode-locking region is confined to the area close to the minimum contrast. Based on these characteristics, an intelligent approach employing a modified gradient algorithm to identify the region of minimum speckle contrast for achieving mode-locked state. The average number of iterations needed to achieve initial mode-locking and recover mode-locking are about 20 and 10, respectively. Once the mode-locking is achieved, the neural network can be employed to distinguish single-pulse or multi-pulses outputs based on the speckle pattern, thereby enabling intelligent stable mode-locked single-pulse genration from the NPR fiber laser.

physics.optics↗

arXiv2023

A Hybrid Deep Feature-Based Deformable Image Registration Method for Pathology Images

Pathologists need to combine information from differently stained pathology slices for accurate diagnosis. Deformable image registration is a necessary technique for fusing multi-modal pathology slices. This paper proposes a hybrid deep feature-based deformable image registration framework for stained pathology samples. We first extract dense feature points via the detector-based and detector-free deep learning feature networks and perform points matching. Then, to further reduce false matches, an outlier detection method combining the isolation forest statistical model and the local affine correction model is proposed. Finally, the interpolation method generates the deformable vector field for pathology image registration based on the above matching points. We evaluate our method on the dataset of the Non-rigid Histology Image Registration (ANHIR) challenge, which is co-organized with the IEEE ISBI 2019 conference. Our technique outperforms the traditional approaches by 17% with the Average-Average registration target error (rTRE) reaching 0.0034. The proposed method achieved state-of-the-art performance and ranked 1st in evaluating the test dataset. The proposed hybrid deep feature-based registration method can potentially become a reliable method for pathology image registration.

eess.IV↗