arXiv subjects

Zhao Zhang

Publications and source records attributed to Zhao Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2024

Lightweight Multiplane Images Network for Real-Time Stereoscopic Conversion from Planar Video

With the rapid development of stereoscopic display technologies, especially glasses-free 3D screens, and virtual reality devices, stereoscopic conversion has become an important task to address the lack of high-quality stereoscopic image and video resources. Current stereoscopic conversion algorithms typically struggle to balance reconstruction performance and inference efficiency. This paper proposes a planar video real-time stereoscopic conversion network based on multi-plane images (MPI), which consists of a detail branch for generating MPI and a depth-semantic branch for perceiving depth information. Unlike models that depend on explicit depth map inputs, the proposed method employs a lightweight depth-semantic branch to extract depth-aware features implicitly. To optimize the lightweight branch, a heavy training but light inference strategy is adopted, which involves designing a coarse-to-fine auxiliary branch that is only used during the training stage. In addition, the proposed method simplifies the MPI rendering process for stereoscopic conversion scenarios to further accelerate the inference. Experimental results demonstrate that the proposed method can achieve comparable performance to some state-of-the-art (SOTA) models and support real-time inference at 2K resolution. Compared to the SOTA TMPI algorithm, the proposed method obtains similar subjective quality while achieving over $40\times$ inference acceleration.

cs.CV↗

arXiv2024

FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning

As trustworthy AI continues to advance, the fairness issue in recommendations has received increasing attention. A recommender system is considered unfair when it produces unequal outcomes for different user groups based on user-sensitive attributes (e.g., age, gender). Some researchers have proposed data augmentation-based methods aiming at alleviating user-level unfairness by altering the skewed distribution of training data among various user groups. Despite yielding promising results, they often rely on fairness-related assumptions that may not align with reality, potentially reducing the data quality and negatively affecting model effectiveness. To tackle this issue, in this paper, we study how to implement high-quality data augmentation to improve recommendation fairness. Specifically, we propose FairDgcl, a dynamic graph adversarial contrastive learning framework aiming at improving fairness in recommender system. First, FairDgcl develops an adversarial contrastive network with a view generator and a view discriminator to learn generating fair augmentation strategies in an adversarial style. Then, we propose two dynamic, learnable models to generate contrastive views within contrastive learning framework, which automatically fine-tune the augmentation strategies. Meanwhile, we theoretically show that FairDgcl can simultaneously generate enhanced representations that possess both fairness and accuracy. Lastly, comprehensive experiments conducted on four real-world datasets demonstrate the effectiveness of the proposed FairDgcl.

cs.AI↗

arXiv2024

Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis

Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently. However, we often observe inconsistent or seemingly contradictory performance findings across different studies. This hinders our understanding of the merits of different approaches and slows down progress. We address the need for means of assessing MTS forecasting proposals reliably and fairly, in turn enabling better exploitation of MTS as seen in different applications. Specifically, we first propose BasicTS+, a benchmark designed to enable fair, comprehensive, and reproducible comparison of MTS forecasting solutions. BasicTS+ establishes a unified training pipeline and reasonable settings, enabling an unbiased evaluation. Second, we identify the heterogeneity across different MTS as an important consideration and enable classification of MTS based on their temporal and spatial characteristics. Disregarding this heterogeneity is a prime reason for difficulties in selecting the most promising technical directions. Third, we apply BasicTS+ along with rich datasets to assess the capabilities of more than 45 MTS forecasting solutions. This provides readers with an overall picture of the cutting-edge research on MTS forecasting. The code can be accessed at https://github.com/GestaltCogTeam/BasicTS.

cs.LG↗

arXiv2024

Synthetic Instance Segmentation from Semantic Image Segmentation Masks

In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In contrast, weakly-supervised instance segmentation methods, such as those using image-level class labels or point labels, often struggle to satisfy the accuracy and recall requirements of practical scenarios. In this paper, we propose a novel paradigm called Synthetic Instance Segmentation (SISeg). SISeg achieves instance segmentation results by leveraging image masks generated by existing semantic segmentation models, and it is highly efficient as we do not require additional training for semantic segmentation or the use of instance-level image annotations. In other words, the proposed model does not need extra manpower or higher computational expenses. Specifically, we first obtain a semantic segmentation mask of the input image via an existent semantic segmentation model. Then, we calculate a displacement field vector for each pixel based on the segmentation mask, which can indicate representations belonging to the same class but different instances, i.e., obtaining the instance-level object information. Finally, the instance segmentation results are refined by a learnable category-agnostic object boundary branch. Extensive experimental results on two challenging datasets highlight the effectiveness of SISeg in achieving competitive results when compared to state-of-the-art methods, especially fully-supervised methods. The code will be released at: SISeg

cs.CV↗

arXiv2024

Quantum lozenge tiling and entanglement phase transition

While volume violation of area law has been exhibited in several quantum spin chains, the construction of a corresponding ground state in higher dimensions, entangled in more than one direction, has been an open problem. Here we construct a 2D frustration-free Hamiltonian with maximal violation of the area law. We do so by building a quantum model of random surfaces with color degree of freedom that can be viewed as a collection of colored Dyck paths. The Hamiltonian may be viewed as a 2D generalization of the Fredkin spin chain. It relates all the colored random surface configurations subject to a Dirichlet boundary condition and hard wall constraint from below to one another, and the ground state is therefore a superposition of all such classical states and non-degenerate. Its entanglement entropy between subsystems undergoes a quantum phase transition as the deformation parameter is tuned. The area- and volume-law phases are similar to the one-dimensional model, while the critical point scales with the linear size of the system $L$ as $L\log L$. Further it is conjectured that similar models with entanglement phase transitions can be built in higher dimensions with even softer area law violations at the critical point.

quant-ph↗

arXiv2024

Motion-Insensitive Time-Optimal Control of Optical Qubits

In trapped-atom quantum computers, high-fidelity control of optical qubits is challenging due to the motion of atoms in the trap. If not corrected, the atom motion gets entangled with the qubit degrees of freedom through two fundamental mechanisms, (i) photon recoil and (ii) thermal motion, both leading to a reduction of the gate fidelity. We develop motion-insensitive pulses that suppress both sources of infidelity by modulating the phase of the driving laser field in time. To eliminate photon recoil, we use bang-bang pulses$-$derived using time-optimal control$-$which shorten the gate duration by about 20 times compared to conventional pulses. However, even when photon recoil is eliminated, we find that the gate error does not vanish, but is rather limited by a bound arising from thermal motion-induced entanglement. Remarkably, this bound is independent of the Rabi frequency, meaning that, unlike for photon recoil, operating in the resolved sideband regime does not mitigate this source of infidelity. To overcome this bound, we derive smooth-phase pulses, which allow for a further reduction of the gate error by more than an order of magnitude for typical thermal atoms. Motion-insensitive pulses can be refined to compensate for laser inhomogeneities, enhancing the gate performance in practical situations. Our results are validated through simulations of one-qubit gates operating on the optical clock transition of ${}^{88}$Sr atoms trapped in an optical tweezers array.

quant-ph↗

arXiv2024

MarsCode Agent: AI-native Automated Bug Fixing

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLMs for automated bug fixing remains challenging due to the complexity and diversity of real-world software systems. In this paper, we introduce MarsCode Agent, a novel framework that leverages LLMs to automatically identify and repair bugs in software code. MarsCode Agent combines the power of LLMs with advanced code analysis techniques to accurately localize faults and generate patches. Our approach follows a systematic process of planning, bug reproduction, fault localization, candidate patch generation, and validation to ensure high-quality bug fixes. We evaluated MarsCode Agent on SWE-bench, a comprehensive benchmark of real-world software projects, and our results show that MarsCode Agent achieves a high success rate in bug fixing compared to most of the existing automated approaches.

cs.SE↗

arXiv2024

Approximation Algorithms for Minimum Sum of Moving-Distance and Opening-Costs Target Coverage Problem

In this paper, we study the Minimum Sum of Moving-Distance and Opening-Costs Target Coverage problem (MinMD$+$OCTC). Given a set of targets and a set of base stations on the plane, an opening cost function for every base station, the opened base stations can emit mobile sensors with a radius of $r$ from base station to cover the targets. The goal of MinMD$+$OCTC is to cover all the targets and minimize the sum of the opening cost and the moving distance of mobile sensors. We give the optimal solution in polynomial time for the MinMD$+$OCTC problem with targets on a straight line, and present a 8.928 approximation algorithm for a special case of the MinMD$+$OCTC problem with the targets on the plane.

cs.CG↗

arXiv2024

A Constant-Approximation Algorithm for Budgeted Sweep Coverage with Mobile Sensors

In this paper, we present the first constant-approximation algorithm for {\em budgeted sweep coverage problem} (BSC). The BSC involves designing routes for a number of mobile sensors (a.k.a. robots) to periodically collect information as much as possible from points of interest (PoIs). To approach this problem, we propose to first examine the {\em multi-orienteering problem} (MOP). The MOP aims to find a set of $m$ vertex-disjoint paths that cover as many vertices as possible while adhering to a budget constraint $B$. We develop a constant-approximation algorithm for MOP and utilize it to achieve a constant-approximation for BSC. Our findings open new possibilities for optimizing mobile sensor deployments and related combinatorial optimization tasks.

cs.DM↗

arXiv2024

Fluctuation-driven dynamics of liquid nano-threads with external hydrodynamic perturbations

Instability and rupture dynamics of a liquid nano-thread, subjected to external hydrodynamic perturbations, are captured by a stochastic lubrication equation (SLE) incorporating thermal fluctuations via Gaussian white noise. Linear instability analysis of the SLE is conducted to derive the spectra and distribution functions of thermal capillary waves influenced by external perturbations and thermal fluctuations. The SLE is also solved numerically using a second-order finite difference method with a correlated noise model. Both theoretical and numerical solutions, validated through molecular dynamics, indicate that surface tension forces due to specific external perturbations overcome the random effects of thermal fluctuations, determining both the thermal capillary waves and the evolution of perturbation growth. The results also show two distinct regimes: (i) the hydrodynamic regime, where external perturbations dominate, leading to uniform ruptures, and (ii) the thermal-fluctuation regime, where external perturbations are surpassed by thermal fluctuations, resulting in non-uniform ruptures. The transition between these regimes, modelled by a criterion developed from the linear instability theory, exhibits a strong dependence on the amplitudes and wavenumbers of the external perturbations.

physics.flu-dyn↗

arXiv2024

Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge

Efficient automatic segmentation of multi-level (i.e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications. However, most existing methods concentrate only on main PA or branch PA segmentation separately and ignore segmentation efficiency. Besides, there is no public large-scale dataset focused on PA segmentation, which makes it highly challenging to compare the different methods. To benchmark multi-level PA segmentation algorithms, we organized the first \textbf{P}ulmonary \textbf{AR}tery \textbf{SE}gmentation (PARSE) challenge. On the one hand, we focus on both the main PA and the branch PA segmentation. On the other hand, for better clinical application, we assign the same score weight to segmentation efficiency (mainly running time and GPU memory consumption during inference) while ensuring PA segmentation accuracy. We present a summary of the top algorithms and offer some suggestions for efficient and accurate multi-level PA automatic segmentation. We provide the PARSE challenge as open-access for the community to benchmark future algorithm developments at \url{https://parse2022.grand-challenge.org/Parse2022/}.

eess.IV↗

arXiv2024

Recoil-free Quantum Gates with Optical Qubits

We propose a scheme to perform optical pulses that suppress the effect of photon recoil by three orders of magnitude compared to ordinary pulses in the Lamb-Dicke regime. We derive analytical insight about the fundamental limits to the fidelity of optical qubits for trapped atoms and ions. This paves the way towards applications in quantum computing for realizing $>1000$ of gates with an overall fidelity above 99\%.

quant-ph↗

arXiv2024

VCHAR:Variance-Driven Complex Human Activity Recognition framework with Generative Representation

Complex human activity recognition (CHAR) remains a pivotal challenge within ubiquitous computing, especially in the context of smart environments. Existing studies typically require meticulous labeling of both atomic and complex activities, a task that is labor-intensive and prone to errors due to the scarcity and inaccuracies of available datasets. Most prior research has focused on datasets that either precisely label atomic activities or, at minimum, their sequence approaches that are often impractical in real world settings.In response, we introduce VCHAR (Variance-Driven Complex Human Activity Recognition), a novel framework that treats the outputs of atomic activities as a distribution over specified intervals. Leveraging generative methodologies, VCHAR elucidates the reasoning behind complex activity classifications through video-based explanations, accessible to users without prior machine learning expertise. Our evaluation across three publicly available datasets demonstrates that VCHAR enhances the accuracy of complex activity recognition without necessitating precise temporal or sequential labeling of atomic activities. Furthermore, user studies confirm that VCHAR's explanations are more intelligible compared to existing methods, facilitating a broader understanding of complex activity recognition among non-experts.

cs.AI↗

arXiv2024

Exploiting Regional Information Transformer for Single Image Deraining

Transformer-based Single Image Deraining (SID) methods have achieved remarkable success, primarily attributed to their robust capability in capturing long-range interactions. However, we've noticed that current methods handle rain-affected and unaffected regions concurrently, overlooking the disparities between these areas, resulting in confusion between rain streaks and background parts, and inabilities to obtain effective interactions, ultimately resulting in suboptimal deraining outcomes. To address the above issue, we introduce the Region Transformer (Regformer), a novel SID method that underlines the importance of independently processing rain-affected and unaffected regions while considering their combined impact for high-quality image reconstruction. The crux of our method is the innovative Region Transformer Block (RTB), which integrates a Region Masked Attention (RMA) mechanism and a Mixed Gate Forward Block (MGFB). Our RTB is used for attention selection of rain-affected and unaffected regions and local modeling of mixed scales. The RMA generates attention maps tailored to these two regions and their interactions, enabling our model to capture comprehensive features essential for rain removal. To better recover high-frequency textures and capture more local details, we develop the MGFB as a compensation module to complete local mixed scale modeling. Extensive experiments demonstrate that our model reaches state-of-the-art performance, significantly improving the image deraining quality. Our code and trained models are publicly available.

cs.CV↗

arXiv2024

A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+

This technical report presents our team's solution for the WeatherProof Dataset Challenge: Semantic Segmentation in Adverse Weather at CVPR'24 UG2+. We propose a two-stage deep learning framework for this task. In the first stage, we preprocess the provided dataset by concatenating images into video sequences. Subsequently, we leverage a low-rank video deraining method to generate high-fidelity pseudo ground truths. These pseudo ground truths offer superior alignment compared to the original ground truths, facilitating model convergence during training. In the second stage, we employ the InternImage network to train for the semantic segmentation task using the generated pseudo ground truths. Notably, our meticulously designed framework demonstrates robustness to degraded data captured under adverse weather conditions. In the challenge, our solution achieved a competitive score of 0.43 on the Mean Intersection over Union (mIoU) metric, securing a respectable rank of 4th.

cs.CV↗

arXiv2024

Aligning Teacher with Student Preferences for Tailored Training Data Generation

Large Language Models (LLMs) have shown significant promise as copilots in various tasks. Local deployment of LLMs on edge devices is necessary when handling privacy-sensitive data or latency-sensitive tasks. The computational constraints of such devices make direct deployment of powerful large-scale LLMs impractical, necessitating the Knowledge Distillation from large-scale models to lightweight models. Lots of work has been done to elicit diversity and quality training examples from LLMs, but little attention has been paid to aligning teacher instructional content based on student preferences, akin to "responsive teaching" in pedagogy. Thus, we propose ARTE, dubbed Aligning TeacheR with StudenT PreferencEs, a framework that aligns the teacher model with student preferences to generate tailored training examples for Knowledge Distillation. Specifically, we elicit draft questions and rationales from the teacher model, then collect student preferences on these questions and rationales using students' performance with in-context learning as a proxy, and finally align the teacher model with student preferences. In the end, we repeat the first step with the aligned teacher model to elicit tailored training examples for the student model on the target task. Extensive experiments on academic benchmarks demonstrate the superiority of ARTE over existing instruction-tuning datasets distilled from powerful LLMs. Moreover, we thoroughly investigate the generalization of ARTE, including the generalization of fine-tuned student models in reasoning ability and the generalization of aligned teacher models to generate tailored training data across tasks and students. In summary, our contributions lie in proposing a novel framework for tailored training example generation, demonstrating its efficacy in experiments, and investigating the generalization of both student & aligned teacher models in ARTE.

cs.CL↗

arXiv2024

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/.

cs.CV↗

arXiv2024

IDVT: Interest-aware Denoising and View-guided Tuning for Social Recommendation

In the information age, recommendation systems are vital for efficiently filtering information and identifying user preferences. Online social platforms have enriched these systems by providing valuable auxiliary information. Socially connected users are assumed to share similar preferences, enhancing recommendation accuracy and addressing cold start issues. However, empirical findings challenge the assumption, revealing that certain social connections can actually harm system performance. Our statistical analysis indicates a significant amount of noise in the social network, where many socially connected users do not share common interests. To address this issue, we propose an innovative \underline{I}nterest-aware \underline{D}enoising and \underline{V}iew-guided \underline{T}uning (IDVT) method for the social recommendation. The first ID part effectively denoises social connections. Specifically, the denoising process considers both social network structure and user interaction interests in a global view. Moreover, in this global view, we also integrate denoised social information (social domain) into the propagation of the user-item interactions (collaborative domain) and aggregate user representations from two domains using a gating mechanism. To tackle potential user interest loss and enhance model robustness within the global view, our second VT part introduces two additional views (local view and dropout-enhanced view) for fine-tuning user representations in the global view through contrastive learning. Extensive evaluations on real-world datasets with varying noise ratios demonstrate the superiority of IDVT over state-of-the-art social recommendation methods.

cs.AI↗