arXiv subjects

Bin Wang

Publications and source records attributed to Bin Wang.

At least 505 records · Page 28Linked to original sources

arXiv2023

Microdisk modulator-assisted optical nonlinear activation functions for photonic neural networks

On-chip implementation of optical nonlinear activation functions (NAFs) is essential for realizing large-scale photonic neural chips. To implement different neural processing and machine learning tasks with optimal performances, different NAFs are explored with the use of different devices. From the perspective of on-chip integration and reconfigurability of photonic neural network (PNN), it is highly preferred that a single compact device can fulfill multiple NAFs. Here, we propose and experimentally demonstrate a compact high-speed microdisk modulator to realize multiple NAFs. The fabricated microdisk modulator has an add-drop configuration in which a lateral PN junction is incorporated for tuning. Based on high-speed nonlinear electrical-optical (E-O) effect, multiple NAFs are realized by electrically controlling free-carrier injection. Thanks to its strong optical confinement of the disk cavity, all-optical thermo-optic (TO) nonlinear effect can also be leveraged to realize other four different NAFs, which is difficult to be realized with the use of electrical-optical effect. With the use of the realized nonlinear activation function, a convolutional neural network (CNN) is studied to perform handwritten digit classification task, and an accuracy as large as 98% is demonstrated, which verifies the effectiveness of the use of the high-speed microdisk modulator to realize the NAFs. Thanks to its compact footprint and strong electrical-optical or all-optical effects, the microdisk modulator features multiple NAFs, which could serve as a flexible nonlinear unit for large-scale PNNs.

physics.optics↗

arXiv2023

Exploring Better Text Image Translation with Multimodal Codebook

Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propose a TIT model with a multimodal codebook, which is able to associate the image with relevant texts, providing useful supplementary information for translation. Moreover, we present a multi-stage training framework involving text machine translation, image-text alignment, and TIT tasks, which fully exploits additional bilingual texts, OCR dataset and our OCRMT30K dataset to train our model. Extensive experiments and in-depth analyses strongly demonstrate the effectiveness of our proposed model and training framework.

cs.CL↗

arXiv2023

MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL

Recently, diffusion model shines as a promising backbone for the sequence modeling paradigm in offline reinforcement learning(RL). However, these works mostly lack the generalization ability across tasks with reward or dynamics change. To tackle this challenge, in this paper we propose a task-oriented conditioned diffusion planner for offline meta-RL(MetaDiffuser), which considers the generalization problem as conditional trajectory generation task with contextual representation. The key is to learn a context conditioned diffusion model which can generate task-oriented trajectories for planning across diverse tasks. To enhance the dynamics consistency of the generated trajectories while encouraging trajectories to achieve high returns, we further design a dual-guided module in the sampling process of the diffusion model. The proposed framework enjoys the robustness to the quality of collected warm-start data from the testing task and the flexibility to incorporate with different task representation method. The experiment results on MuJoCo benchmarks show that MetaDiffuser outperforms other strong offline meta-RL baselines, demonstrating the outstanding conditional generation ability of diffusion architecture.

cs.LG↗

arXiv2023

MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions

Morality in dialogue systems has raised great attention in research recently. A moral dialogue system aligned with users' values could enhance conversation engagement and user connections. In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems. In our framework, we first explore the communication mechanisms of morality and resolve expressed morality into three parts, which indicate the roadmap for building a moral dialogue system. Based on that, we design a simple yet effective method: constructing moral discussions between simulated specific users and the dialogue system. The constructed discussions consist of expressing, explaining, revising, and inferring moral views in dialogue exchanges, which makes conversational models learn morality well in a natural manner. Furthermore, we propose a novel evaluation method under the framework. We evaluate the multiple aspects of morality by judging the relation between dialogue responses and human values in discussions, where the multifaceted nature of morality is particularly considered. Automatic and manual experiments demonstrate that our framework is promising to train and evaluate moral dialogue systems.

cs.CL↗

arXiv2023

Pay More Attention to Relation Exploration for Knowledge Base Question Answering

Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, which empirically determine the reasoning path selection, are not fully considered in recent advancements. In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision. We explore guidance from relations in three aspects, including (1) distinguishing similar entities by employing a variational graph auto-encoder to learn relation importance; (2) exploring extra supervision by predicting relation distributions as soft labels with a multi-task scheme; (3) designing a relation-guided re-ranking algorithm for post-processing. Experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our framework, improving the F1 score by 5.7% from 40.5 to 46.3 on CWQ and 5.8% from 62.8 to 68.5 on WebQSP, better or on par with state-of-the-art methods.

cs.CL↗

arXiv2023

A Multi-stage Transfer Learning Framework for Diabetic Retinopathy Grading on Small Data

Diabetic retinopathy (DR) is one of the major blindness-causing diseases currently known. Automatic grading of DR using deep learning methods not only speeds up the diagnosis of the disease but also reduces the rate of misdiagnosis. However,problems such as insufficient samples and imbalanced class distribution in small DR datasets have constrained the improvement of grading performance. In this paper, we apply the idea of multi-stage transfer learning into the grading task of DR. The new transfer learning technique utilizes multiple datasets with different scales to enable the model to learn more feature representation information. Meanwhile, to cope with the imbalanced problem of small DR datasets, we present a class-balanced loss function in our work and adopt a simple and easy-to-implement training method for it. The experimental results on IDRiD dataset show that our method can effectively improve the grading performance on small data, obtaining scores of 0.7961 and 0.8763 in terms of accuracy and quadratic weighted kappa, respectively. Our method also outperforms several state-of-the-art methods.

eess.IV↗

arXiv2023

Transversal Hamilton cycle in hypergraph systems

A $k$-graph system $\textbf{H}=\{H_i\}_{i\in[m]}$ is a family of not necessarily distinct $k$-graphs on the same $n$-vertex set $V$ and a $k$-graph $H$ on $V$ is said to be $\textbf{H}$-transversal provided that there exists an injection $φ: E(H)\rightarrow [m]$ such that $e\in E(H_{φ(e)})$ for all $e\in E(H)$. We show that given $k\geq3, γ>0$, sufficiently large $n$ and an $n$-vertex $k$-graph system $\textbf{H}=\{H_i\}_{i\in[n]}$, if $δ_{k-1}(H_i)\geq(1/2+γ)n$ for each $i\in[n]$, then there exists an $\textbf{H}$-transversal tight Hamilton cycle. This extends the result of Rödl, Ruciński and Szemerédi [Combinatorica, 2008] on single $k$-graphs.

math.CO↗

arXiv2023

Detecting the secondary spin with extreme mass ratio inspirals in Scalar-Tensor theory

In this paper, we investigate the detectability of secondary spin in the extreme mass ratio inspirals system within a modified gravity model coupled with a scalar field. The central black hole, which reduces to a Kerr one, is circularly spiralled by a scalar-charged spinning secondary body on the equatorial plane. The analysis reveals that the presence of the scalar field amplifies the secondary spin effect, allowing for a lower limit of the detectability and an improved resolution of the secondary spin when the scalar charge is sufficiently large. Our findings suggest that the secondary spin detection is more feasible when the primary mass is not large, and TianQin is the optimal choice for detection.

gr-qc↗

arXiv2023

Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation

Oriented normals are common pre-requisites for many geometric algorithms based on point clouds, such as Poisson surface reconstruction. However, it is not trivial to obtain a consistent orientation. In this work, we bridge orientation and reconstruction in the implicit space and propose a novel approach to orient point cloud normals by incorporating isovalue constraints to the Poisson equation. In implicit surface reconstruction, the reconstructed shape is represented as an isosurface of an implicit function defined in the ambient space. Therefore, when such a surface is reconstructed from a set of sample points, the implicit function values at the points should be close to the isovalue corresponding to the surface. Based on this observation and the Poisson equation, we propose an optimization formulation that combines isovalue constraints with local consistency requirements for normals. We optimize normals and implicit functions simultaneously and solve for a globally consistent orientation. Thanks to the sparsity of the linear system, our method can work on an average laptop with reasonable computational time. Experiments show that our method can achieve high performance in non-uniform and noisy data and manage varying sampling densities, artifacts, multiple connected components, and nested surfaces. The source code is available at \url{https://github.com/Submanifold/IsoConstraints}.

cs.GR↗

arXiv2023

GazeSAM: What You See is What You Segment

This study investigates the potential of eye-tracking technology and the Segment Anything Model (SAM) to design a collaborative human-computer interaction system that automates medical image segmentation. We present the \textbf{GazeSAM} system to enable radiologists to collect segmentation masks by simply looking at the region of interest during image diagnosis. The proposed system tracks radiologists' eye movement and utilizes the eye-gaze data as the input prompt for SAM, which automatically generates the segmentation mask in real time. This study is the first work to leverage the power of eye-tracking technology and SAM to enhance the efficiency of daily clinical practice. Moreover, eye-gaze data coupled with image and corresponding segmentation labels can be easily recorded for further advanced eye-tracking research. The code is available in \url{https://github.com/ukaukaaaa/GazeSAM}.

cs.CV↗

arXiv2023

A two-generational ${\rm SU}(7)$ model with extended weak sector: mass hierarchies, mixings, and the flavor non-universality

We study a possible gauge symmetry breaking pattern in an ${\rm SU}(7)$ grand unified theory, which describes the mass origins of all electrically charged SM fermions of the second and the third generations. Two intermediate gauge symmetries of ${\cal G}_{341}\equiv {\rm SU}(3)_c \otimes {\rm SU}(4)_W \otimes {\rm U}(1)_{X_0}$ and ${\cal G}_{331}\equiv {\rm SU}(3)_c \otimes {\rm SU}(3)_W \otimes {\rm U}(1)_{X_1}$ arise above the electroweak scale. SM fermion mass hierarchies between two generations can be obtained through a generalized seesaw mechanism. The mechanism can be achieved with suppressed symmetry breaking VEVs from multiple Higgs fields that are necessary to avoid tadpole terms in the Higgs potential. Some general features of the ${\rm SU}(7)$ fermion spectrum will be described, which include the existence of vectorlike fermions, the tree-level flavor changing weak currents between the SM fermions and heavy partner fermions, and the flavor non-universality between different SM generations from the extended weak sector.

hep-ph↗

arXiv2023

Real-time Multi-Class Helmet Violation Detection Using Few-Shot Data Sampling Technique and YOLOv8

Traffic safety is a major global concern. Helmet usage is a key factor in preventing head injuries and fatalities caused by motorcycle accidents. However, helmet usage violations continue to be a significant problem. To identify such violations, automatic helmet detection systems have been proposed and implemented using computer vision techniques. Real-time implementation of such systems is crucial for traffic surveillance and enforcement, however, most of these systems are not real-time. This study proposes a robust real-time helmet violation detection system. The proposed system utilizes a unique data processing strategy, referred to as few-shot data sampling, to develop a robust model with fewer annotations, and a single-stage object detection model, YOLOv8 (You Only Look Once Version 8), for detecting helmet violations in real-time from video frames. Our proposed method won 7th place in the 2023 AI City Challenge, Track 5, with an mAP score of 0.5861 on experimental validation data. The experimental results demonstrate the effectiveness, efficiency, and robustness of the proposed system.

cs.CV↗

arXiv2023

Contrastive Cross-Domain Sequential Recommendation

Cross-Domain Sequential Recommendation (CDSR) aims to predict future interactions based on user's historical sequential interactions from multiple domains. Generally, a key challenge of CDSR is how to mine precise cross-domain user preference based on the intra-sequence and inter-sequence item interactions. Existing works first learn single-domain user preference only with intra-sequence item interactions, and then build a transferring module to obtain cross-domain user preference. However, such a pipeline and implicit solution can be severely limited by the bottleneck of the designed transferring module, and ignores to consider inter-sequence item relationships. In this paper, we propose C^2DSR to tackle the above problems to capture precise user preferences. The main idea is to simultaneously leverage the intra- and inter- sequence item relationships, and jointly learn the single- and cross- domain user preferences. Specifically, we first utilize a graph neural network to mine inter-sequence item collaborative relationship, and then exploit sequential attentive encoder to capture intra-sequence item sequential relationship. Based on them, we devise two different sequential training objectives to obtain user single-domain and cross-domain representations. Furthermore, we present a novel contrastive cross-domain infomax objective to enhance the correlation between single- and cross- domain user representations by maximizing their mutual information. To validate the effectiveness of C^2DSR, we first re-split four e-comerce datasets, and then conduct extensive experiments to demonstrate the effectiveness of our approach C^2DSR.

cs.IR↗

arXiv2023

Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation

Most statistical learning algorithms rely on an over-simplified assumption, that is, the train and test data are independent and identically distributed. In real-world scenarios, however, it is common for models to encounter data from new and different domains to which they were not exposed to during training. This is often the case in medical imaging applications due to differences in acquisition devices, imaging protocols, and patient characteristics. To address this problem, domain generalization (DG) is a promising direction as it enables models to handle data from previously unseen domains by learning domain-invariant features robust to variations across different domains. To this end, we introduce a novel DG method called Adversarial Intensity Attack (AdverIN), which leverages adversarial training to generate training data with an infinite number of styles and increase data diversity while preserving essential content information. We conduct extensive evaluation experiments on various multi-domain segmentation datasets, including 2D retinal fundus optic disc/cup and 3D prostate MRI. Our results demonstrate that AdverIN significantly improves the generalization ability of the segmentation models, achieving significant improvement on these challenging datasets. Code is available upon publication.

eess.IV↗

arXiv2023

Knowledge Graph Embedding with 3D Compound Geometric Transformations

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE model, Rotate3D, by leveraging its non-commutative property. Inspired by CompoundE and Rotate3D, we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.

cs.AI↗

arXiv2023

Multi-Microgrid Collaborative Optimization Scheduling Using an Improved Multi-Agent Soft Actor-Critic Algorithm

The implementation of a multi-microgrid (MMG) system with multiple renewable energy sources enables the facilitation of electricity trading. To tackle the energy management problem of a MMG system, which consists of multiple renewable energy microgrids belonging to different operating entities, this paper proposes a MMG collaborative optimization scheduling model based on a multi-agent centralized training distributed execution framework. To enhance the generalization ability of dealing with various uncertainties, we also propose an improved multi-agent soft actor-critic (MASAC) algorithm, which facilitates en-ergy transactions between multi-agents in MMG, and employs automated machine learning (AutoML) to optimize the MASAC hyperparameters to further improve the generalization of deep reinforcement learning (DRL). The test results demonstrate that the proposed method successfully achieves power complementarity between different entities, and reduces the MMG system operating cost. Additionally, the proposal significantly outperforms other state-of-the-art reinforcement learning algorithms with better economy and higher calculation efficiency.

eess.SY↗

arXiv2023

Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance. Previous works focus on either single task model pruning or simply adapting it to multitask scenario, and still face the following problems when handling multitask pruning: 1) Due to the task mismatch, a well-pruned backbone for classification task focuses on preserving filters that can extract category-sensitive information, causing filters that may be useful for other tasks to be pruned during the backbone pruning stage; 2) For multitask predictions, different filters within or between layers are more closely related and interacted than that for single task prediction, making multitask pruning more difficult. Therefore, aiming at multitask model compression, we propose a Performance-Aware Global Channel Pruning (PAGCP) framework. We first theoretically present the objective for achieving superior GCP, by considering the joint saliency of filters from intra- and inter-layers. Then a sequentially greedy pruning strategy is proposed to optimize the objective, where a performance-aware oracle criterion is developed to evaluate sensitivity of filters to each task and preserve the globally most task-related filters. Experiments on several multitask datasets show that the proposed PAGCP can reduce the FLOPs and parameters by over 60% with minor performance drop, and achieves 1.2x$\sim$3.3x acceleration on both cloud and mobile platforms.

cs.CV↗

arXiv2023

A Spatio-temporal Decomposition Method for the Coordinated Economic Dispatch of Integrated Transmission and Distribution Grids

With numerous distributed energy resources (DERs) integrated into the distribution networks (DNs), the coordinated economic dispatch (C-ED) is essential for the integrated transmission and distribution grids. For large scale power grids, the centralized C-ED meets high computational burden and information privacy issues. To tackle these issues, this paper proposes a spatio-temporal decomposition algorithm to solve the C-ED in a distributed and parallel manner. In the temporal dimension, the multi-period economic dispatch (ED) of transmission grid (TG) is decomposed to several subproblems by introducing auxiliary variables and overlapping time intervals to deal with the temporal coupling constraints. Besides, an accelerated alternative direction method of multipliers (A-ADMM) based temporal decomposition algorithm with the warm-start strategy, is developed to solve the ED subproblems of TG in parallel. In the spatial dimension, a multi-parametric programming projection based spatial decomposition algorithm is developed to coordinate the ED problems of TG and DNs in a distributed manner. To further improve the convergence performance of the spatial decomposition algorithm, the aggregate equivalence approach is used for determining the feasible range of boundary variables of TG and DNs. Moreover, we prove that the proposed spatio-temporal decomposition method can obtain the optimal solution for bilevel convex optimization problems with continuously differentiable objectives and constraints. Numerical tests are conducted on three systems with different scales, demonstrating the high computational efficiency and scalability of the proposed spatio-temporal decomposition method.

eess.SY↗