arXiv subjects

Zhao Zhang

Publications and source records attributed to Zhao Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2023

Fine-grained Policy-driven I/O Sharing for Burst Buffers

A burst buffer is a common method to bridge the performance gap between the I/O needs of modern supercomputing applications and the performance of the shared file system on large-scale supercomputers. However, existing I/O sharing methods require resource isolation, offline profiling, or repeated execution that significantly limit the utilization and applicability of these systems. Here we present ThemisIO, a policy-driven I/O sharing framework for a remote-shared burst buffer: a dedicated group of I/O nodes, each with a local storage device. ThemisIO preserves high utilization by implementing opportunity fairness so that it can reallocate unused I/O resources to other applications. ThemisIO accurately and efficiently allocates I/O cycles among applications, purely based on real-time I/O behavior without requiring user-supplied information or offline-profiled application characteristics. ThemisIO supports a variety of fair sharing policies, such as user-fair, size-fair, as well as composite policies, e.g., group-then-user-fair. All these features are enabled by its statistical token design. ThemisIO can alter the execution order of incoming I/O requests based on assigned tokens to precisely balance I/O cycles between applications via time slicing, thereby enforcing processing isolation. Experiments using I/O benchmarks show that ThemisIO sustains 13.5-13.7% higher I/O throughput and 19.5-40.4% lower performance variation than existing algorithms. For real applications, ThemisIO significantly reduces the slowdown by 59.1-99.8% caused by I/O interference.

cs.DC↗

arXiv2023

Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers

Breast ultrasound videos contain richer information than ultrasound images, therefore it is more meaningful to develop video models for this diagnosis task. However, the collection of ultrasound video datasets is much harder. In this paper, we explore the feasibility of enhancing the performance of ultrasound video classification using the static image dataset. To this end, we propose KGA-Net and coherence loss. The KGA-Net adopts both video clips and static images to train the network. The coherence loss uses the feature centers generated by the static images to guide the frame attention in the video model. Our KGA-Net boosts the performance on the public BUSV dataset by a large margin. The visualization results of frame attention prove the explainability of our method. The codes and model weights of our method will be made publicly available.

cs.CV↗

arXiv2023

Advancing Referring Expression Segmentation Beyond Single Image

Referring Expression Segmentation (RES) is a widely explored multi-modal task, which endeavors to segment the pre-existing object within a single image with a given linguistic expression. However, in broader real-world scenarios, it is not always possible to determine if the described object exists in a specific image. Typically, we have a collection of images, some of which may contain the described objects. The current RES setting curbs its practicality in such situations. To overcome this limitation, we propose a more realistic and general setting, named Group-wise Referring Expression Segmentation (GRES), which expands RES to a collection of related images, allowing the described objects to be present in a subset of input images. To support this new setting, we introduce an elaborately compiled dataset named Grouped Referring Dataset (GRD), containing complete group-wise annotations of target objects described by given expressions. We also present a baseline method named Grouped Referring Segmenter (GRSer), which explicitly captures the language-vision and intra-group vision-vision interactions to achieve state-of-the-art results on the proposed GRES and related tasks, such as Co-Salient Object Detection and RES. Our dataset and codes will be publicly released in https://github.com/yixuan730/group-res.

cs.CV↗

arXiv2023

Attacking Pre-trained Recommendation

Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks. Despite these advancements, the vulnerabilities of classical recommender systems also exist in pre-trained recommendation in a new form, while the security of pre-trained recommendation model is still unexplored, which may threaten its widely practical applications. In this study, we propose a novel framework for backdoor attacking in pre-trained recommendation. We demonstrate the provider of the pre-trained model can easily insert a backdoor in pre-training, thereby increasing the exposure rates of target items to target user groups. Specifically, we design two novel and effective backdoor attacks: basic replacement and prompt-enhanced, under various recommendation pre-training usage scenarios. Experimental results on real-world datasets show that our proposed attack strategies significantly improve the exposure rates of target items to target users by hundreds of times in comparison to the clean model.

cs.IR↗

arXiv2023

A Hybrid Physics Machine Learning Approach for Macroscopic Traffic State Estimation

Full-field traffic state information (i.e., flow, speed, and density) is critical for the successful operation of Intelligent Transportation Systems (ITS) on freeways. However, incomplete traffic information tends to be directly collected from traffic detectors that are insufficiently installed in most areas, which is a major obstacle to the popularization of ITS. To tackle this issue, this paper introduces an innovative traffic state estimation (TSE) framework that hybrid regression machine learning techniques (e.g., artificial neural network (ANN), random forest (RF), and support vector machine (SVM)) with a traffic physics model (e.g., second-order macroscopic traffic flow model) using limited information from traffic sensors as inputs to construct accurate and full-field estimated traffic state for freeway systems. To examine the effectiveness of the proposed TSE framework, this paper conducted empirical studies on a real-world data set collected from a stretch of I-15 freeway in Salt Lake City, Utah. Experimental results show that the proposed method has been proved to estimate full-field traffic information accurately. Hence, the proposed method could provide accurate and full-field traffic information, thus providing the basis for the popularization of ITS.

cs.LG↗

arXiv2023

The frustration-free fully packed loop model

We consider a quantum fully packed loop model on the square lattice with a frustration-free projector Hamiltonian and ring-exchange interactions acting on plaquettes. A boundary Hamiltonian is added to favour domain-wall boundary conditions and link ground state properties to the combinatorics and six-vertex model literature. We discuss how the boundary term fractures the Hilbert space into Krylov subspaces, and we prove that the Hamiltonian is ergodic within each subspace, leading to a series of energy-equidistant exact eigenstates in the lower end of the spectrum. Among them we systematically classify both finitely entangled eigenstates and product eigenstates. Using a recursion relation for enumerating half-plane configurations, we compute numerically the exact entanglement entropy of the ground state, confirming area law scaling. Finally, the spectrum is shown to be gapless in the thermodynamic limit with a trial state constructed by adding a twist to the ground state superposition.

cond-mat.stat-mech↗

arXiv2023

Coupled Fredkin and Motzkin chains from quantum six- and nineteen-vertex models

We generalize the area-law violating models of Fredkin and Motzkin spin chains into two dimensions by building quantum six- and nineteen-vertex models with correlated interactions. The Hamiltonian is frustration free, and its projectors generate ergodic dynamics within the subspace of height configuration that are non negative. The ground state is a volume- and color-weighted superposition of classical bi-color vertex configurations with non-negative heights in the bulk and zero height on the boundary. The entanglement entropy between subsystems has a phase transition as the $q$-deformation parameter is tuned, which is shown to be robust in the presence of an external field acting on the color degree of freedom. The ground state undergoes a quantum phase transition between area- and volume-law entanglement phases with a critical point where entanglement entropy scales as a function $L\log L$ of the linear system size $L$. Intermediate power law scalings between $L\log L$ and $L^2$ can be achieved with an inhomogeneous deformation parameter that approaches 1 at different rates in the thermodynamic limit. For the $q>1$ phase, we construct a variational wave function that establishes an upper bound on the spectral gap that scales as $q^{-L^3/8}$.

quant-ph↗

arXiv2023

Co-Salient Object Detection with Co-Representation Purification

Co-salient object detection (Co-SOD) aims at discovering the common objects in a group of relevant images. Mining a co-representation is essential for locating co-salient objects. Unfortunately, the current Co-SOD method does not pay enough attention that the information not related to the co-salient object is included in the co-representation. Such irrelevant information in the co-representation interferes with its locating of co-salient objects. In this paper, we propose a Co-Representation Purification (CoRP) method aiming at searching noise-free co-representation. We search a few pixel-wise embeddings probably belonging to co-salient regions. These embeddings constitute our co-representation and guide our prediction. For obtaining purer co-representation, we use the prediction to iteratively reduce irrelevant embeddings in our co-representation. Experiments on three datasets demonstrate that our CoRP achieves state-of-the-art performances on the benchmark datasets. Our source code is available at https://github.com/ZZY816/CoRP.

cs.CV↗

arXiv2023

A New Approximation Algorithm for Minimum-Weight $(1,m)$--Connected Dominating Set

Consider a graph with nonnegative node weight. A vertex subset is called a CDS (connected dominating set) if every other node has at least one neighbor in the subset and the subset induces a connected subgraph. Furthermore, if every other node has at least $m$ neighbors in the subset, then the node subset is called a $(1,m)$CDS. The minimum-weight $(1,m)$CDS problem aims at finding a $(1,m)$CDS with minimum total node weight. In this paper, we present a new polynomial-time approximation algorithm for this problem with approximation ratio $2H(δ_{\max}+m-1)$, where $δ_{\max}$ is the maximum degree of the given graph and $H(\cdot)$ is the Harmonic function, i.e., $H(k)=\sum_{i=1}^k \frac{1}{i}$.

cs.DS↗

arXiv2023

A Game-Theoretic Approach to Solving the Roman Domination Problem

The Roamn domination problem is one important combinatorial optimization problem that is derived from an old story of defending the Roman Empire and now regains new significance in cyber space security, considering backups in the face of a dynamic network security requirement. In this paper, firstly, we propose a Roman domination game (RDG) and prove that every Nash equilibrium (NE) of the game corresponds to a strong minimal Roman dominating function (S-RDF), as well as a Pareto-optimal solution. Secondly, we show that RDG is an exact potential game, which guarantees the existence of an NE. Thirdly, we design a game-based synchronous algorithm (GSA), which can be implemented distributively and converge to an NE in $O(n)$ rounds, where $n$ is the number of vertices. In GSA, all players make decisions depending on the local information. Furthermore, we enhance GSA to be enhanced GSA (EGSA), which converges to a better NE in $O(n^2)$ rounds. Finally, we present numerical simulations to demonstrate that EGSA can obtain a better approximate solution in promising computation time compared with state-of-the-art algorithms.

cs.GT↗

arXiv2023

A Ray-tracing and Deep Learning Fusion Super-resolution Modeling Method for Wireless Mobile Channel

Mobile channel modeling has always been the core part for design, deployment and optimization of communication system, especially in 5G and beyond era. Deterministic channel modeling could precisely achieve mobile channel description, however with defects of equipment and time consuming. In this paper, we proposed a novel super resolution (SR) model for cluster characteristics prediction. The model is based on deep neural networks with residual connection. A series of simulations at 3.5 GHz are conducted by a three-dimensional ray tracing (RT) simulator in diverse scenarios. Cluster characteristics are extracted and corresponding data sets are constructed to train the model. Experiments demonstrate that the proposed SR approach could achieve better power and cluster location prediction performance than traditional interpolation method and the root mean square error (RMSE) drops by 51% and 78% relatively. Channel impulse response (CIR) is reconstructed based on cluster characteristics, which could match well with the multi-path component (MPC). The proposed method can be used to efficiently and accurately generate big data of mobile channel, which significantly reduces the computation time of RT-only.

eess.SP↗

arXiv2022

On Deep Recurrent Reinforcement Learning for Active Visual Tracking of Space Noncooperative Objects

Active tracking of space noncooperative object that merely relies on vision camera is greatly significant for autonomous rendezvous and debris removal. Considering its Partial Observable Markov Decision Process (POMDP) property, this paper proposes a novel tracker based on deep recurrent reinforcement learning, named as RAMAVT which drives the chasing spacecraft to follow arbitrary space noncooperative object with high-frequency and near-optimal velocity control commands. To further improve the active tracking performance, we introduce Multi-Head Attention (MHA) module and Squeeze-and-Excitation (SE) layer into RAMAVT, which remarkably improve the representative ability of neural network with almost no extra computational cost. Extensive experiments and ablation study implemented on SNCOAT benchmark show the effectiveness and robustness of our method compared with other state-of-the-art algorithm. The source codes are available on https://github.com/Dongzhou-1996/RAMAVT.

cs.RO↗

arXiv2022

Stereo Image Rain Removal via Dual-View Mutual Attention

Stereo images, containing left and right view images with disparity, are utilized in solving low-vision tasks recently, e.g., rain removal and super-resolution. Stereo image restoration methods usually obtain better performance than monocular methods by learning the disparity between dual views either implicitly or explicitly. However, existing stereo rain removal methods still cannot make full use of the complementary information between two views, and we find it is because: 1) the rain streaks have more complex distributions in directions and densities, which severely damage the complementary information and pose greater challenges; 2) the disparity estimation is not accurate enough due to the imperfect fusion mechanism for the features between two views. To overcome such limitations, we propose a new \underline{Stereo} \underline{I}mage \underline{R}ain \underline{R}emoval method (StereoIRR) via sufficient interaction between two views, which incorporates: 1) a new Dual-view Mutual Attention (DMA) mechanism which generates mutual attention maps by taking left and right views as key information for each other to facilitate cross-view feature fusion; 2) a long-range and cross-view interaction, which is constructed with basic blocks and dual-view mutual attention, can alleviate the adverse effect of rain on complementary information to help the features of stereo images to get long-range and cross-view interaction and fusion. Notably, StereoIRR outperforms other related monocular and stereo image rain removal methods on several datasets. Our codes and datasets will be released.

cs.CV↗

arXiv2022

Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous methods (such as quantization aware training and post training quantization) require original data for the fine-tuning or calibration of quantized model, which makes them inapplicable to the cases that original data are not accessed due to privacy or security. This gives birth to the data-free quantization method with synthetic data generation. While current data-free quantization methods still suffer from severe performance degradation when quantizing a model into lower bit, caused by the low inter-class separability of semantic features. To this end, we propose a new and effective data-free quantization method termed ClusterQ, which utilizes the feature distribution alignment for synthetic data generation. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics to imitate the distribution of real data, so that the performance degradation is alleviated. Moreover, we incorporate the diversity enhancement to solve class-wise mode collapse. We also employ the exponential moving average to update the centroid of each cluster for further feature distribution improvement. Extensive experiments based on different deep models (e.g., ResNet-18 and MobileNet-V2) over the ImageNet dataset demonstrate that our proposed ClusterQ model obtains state-of-the-art performance.

cs.CV↗

arXiv2022

Heterogeneous Graph Neural Network with Multi-view Representation Learning

Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph embedding methods either insufficiently model the local structure under specific semantic, or neglect the heterogeneity when aggregating information from it. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain versatile node embeddings. To address the problem, we propose a Heterogeneous Graph Neural Network with Multi-View Representation Learning (named MV-HetGNN) for heterogeneous graph embedding by introducing the idea of multi-view representation learning. The proposed model consists of node feature transformation, view-specific ego graph encoding and auto multi-view fusion to thoroughly learn complex structural and semantic information for generating comprehensive node representations. Extensive experiments on three real-world heterogeneous graph datasets show that the proposed MV-HetGNN model consistently outperforms all the state-of-the-art GNN baselines in various downstream tasks, e.g., node classification, node clustering, and link prediction.

cs.LG↗

arXiv2022

Long-Range Zero-Shot Generative Deep Network Quantization

Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers, in order to accelerate inference and reduce computation. Quantizing a model without access to the original data, zero-shot quantization can be accomplished by fitting the real data distribution by data synthesis. However, zero-shot quantization achieves inferior performance compared to the post-training quantization with real data. We find it is because: 1) a normal generator is hard to obtain high diversity of synthetic data, since it lacks long-range information to allocate attention to global features; 2) the synthetic images aim to simulate the statistics of real data, which leads to weak intra-class heterogeneity and limited feature richness. To overcome these problems, we propose a novel deep network quantizer, dubbed Long-Range Zero-Shot Generative Deep Network Quantization (LRQ). Technically, we propose a long-range generator to learn long-range information instead of simple local features. In order for the synthetic data to contain more global features, long-range attention using large kernel convolution is incorporated into the generator. In addition, we also present an Adversarial Margin Add (AMA) module to force intra-class angular enlargement between feature vector and class center. As AMA increases the convergence difficulty of the loss function, which is opposite to the training objective of the original loss function, it forms an adversarial process. Furthermore, in order to transfer knowledge from the full-precision network, we also utilize a decoupled knowledge distillation. Extensive experiments demonstrate that LRQ obtains better performance than other competitors.

cs.CV↗

arXiv2022

Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising

Low-light image enhancement (LLIE) aims at improving the illumination and visibility of dark images with lighting noise. To handle the real-world low-light images often with heavy and complex noise, some efforts have been made for joint LLIE and denoising, which however only achieve inferior restoration performance. We attribute it to two challenges: 1) in real-world low-light images, noise is somewhat covered by low-lighting and the left noise after denoising would be inevitably amplified during enhancement; 2) conversion of raw data to sRGB would cause information loss and also more noise, and hence prior LLIE methods trained on raw data are unsuitable for more common sRGB images. In this work, we propose a novel Low-light Enhancement & Denoising Network for real-world low-light images (RLED-Net) in the sRGB color space. In RLED-Net, we apply a plug-and-play differentiable Latent Subspace Reconstruction Block (LSRB) to embed the real-world images into low-rank subspaces to suppress the noise and rectify the errors, such that the impact of noise during enhancement can be effectively shrunk. We then present an efficient Crossed-channel & Shift-window Transformer (CST) layer with two branches to calculate the window and channel attentions to resist the degradation (e.g., speckle noise and blur) caused by the noise in input images. Based on the CST layers, we further present a U-structure network CSTNet as backbone for deep feature recovery, and construct a feature refine block to refine the final features. Extensive experiments on both real noisy images and public image databases well verify the effectiveness of the proposed RLED-Net for RLLIE and denoising simultaneously.

cs.CV↗

arXiv2022

Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in The Dark

Low-light stereo image enhancement (LLSIE) is a relatively new task to enhance the quality of visually unpleasant stereo images captured in dark condition. However, current methods achieve inferior performance on detail recovery and illumination adjustment. We find it is because: 1) the insufficient single-scale inter-view interaction makes the cross-view cues unable to be fully exploited; 2) lacking long-range dependency leads to the inability to deal with the spatial long-range effects caused by illumination degradation. To alleviate such limitations, we propose a LLSIE model termed Decoupled Cross-scale Cross-view Interaction Network (DCI-Net). Specifically, we present a decoupled interaction module (DIM) that aims for sufficient dual-view information interaction. DIM decouples the dual-view information exchange into discovering multi-scale cross-view correlations and further exploring cross-scale information flow. Besides, we present a spatial-channel information mining block (SIMB) for intra-view feature extraction, and the benefits are twofold. One is the long-range dependency capture to build spatial long-range relationship, and the other is expanded channel information refinement that enhances information flow in channel dimension. Extensive experiments on Flickr1024, KITTI 2012, KITTI 2015 and Middlebury datasets show that our method obtains better illumination adjustment and detail recovery, and achieves SOTA performance compared to other related methods. Our codes, datasets and models will be publicly available.

cs.CV↗