arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 1,243 records · Page 69Linked to original sources

arXiv2022

Event-triggered Consensus Control of Heterogeneous Multi-agent Systems: Model- and Data-based Analysis

This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme. A dynamic periodic transmission protocol is developed to significantly alleviate the transmission frequency and computational burden, where the followers can interact locally with each other approaching the dynamics of the leader. Capitalizing on a discrete-time looped-functional, a model-based consensus condition for the closed-loop MASs is derived in form of linear matrix inequalities (LMIs), as well as a design method for obtaining the distributed controllers and event-triggering parameters. Upon collecting noise-corrupted state-input measurements during open-loop operation, a data-driven leader-following MAS representation is presented, and employed to solve the data-driven consensus control problem without requiring any knowledge of the agents' models. This result is then extended to the case of guaranteeing an $\mathcal{H}_{\infty}$ performance. A simulation example is finally given to corroborate the efficacy of the proposed distributed event-triggering scheme in cutting off data transmissions and the data-driven design method.

eess.SY↗

arXiv2022

Trajectory Planning of Cellular-Connected UAV for Communication-assisted Radar Sensing

Being a key technology for beyond fifth-generation wireless systems, joint communication and radar sensing (JCAS) utilizes the reflections of communication signals to detect foreign objects and deliver situational awareness. A cellular-connected unmanned aerial vehicle (UAV) is uniquely suited to form a mobile bistatic synthetic aperture radar (SAR) with its serving base station (BS) to sense over large areas with superb sensing resolutions at no additional requirement of spectrum. This paper designs this novel BS-UAV bistatic SAR platform, and optimizes the flight path of the UAV to minimize its propulsion energy and guarantee the required sensing resolutions on a series of interesting landmarks. A new trajectory planning algorithm is developed to convexify the propulsion energy and resolution requirements by using successive convex approximation and block coordinate descent. Effective trajectories are obtained with a polynomial complexity. Extensive simulations reveal that the proposed trajectory planning algorithm outperforms significantly its alternative that minimizes the flight distance of cellular-aided sensing missions in terms of energy efficiency and effective consumption fluctuation. The energy saving offered by the proposed algorithm can be as significant as 55\%.

eess.SY↗

arXiv2022

Early results from GLASS-JWST. IX: First spectroscopic confirmation of low-mass quiescent galaxies at $z>2$ with NIRISS

How passive galaxies form, and the physical mechanisms which prevent star formation over long timescales, are some of the most outstanding questions in understanding galaxy evolution. The properties of quiescent galaxies over cosmic time provide crucial information to identify the quenching mechanisms. Passive galaxies have been confirmed and studied out to $z\sim4$, but all of these studies have been limited to massive systems (mostly with $\log{(M_{\rm star}/M_{\odot})}>10.8$). Using James Webb Space Telescope (JWST) NIRISS grism slitless spectroscopic data from the GLASS JWST ERS program, we present spectroscopic confirmation of two quiescent galaxies at $z_{\rm spec}=2.650^{+0.004}_{-0.006}$ and $z_{\rm spec}=2.433^{+0.032}_{-0.016}$ (3$σ$ errors) with stellar masses of $\log{(M_{\rm star}/M_{\odot})}=10.53^{+0.18}_{-0.06}$ and $\log{(M_{\rm star}/M_{\odot})}=9.93^{+0.06}_{-0.07}$ (corrected for magnification factors of $μ=2.0$ and $μ=2.1$, respectively). The latter represents the first spectroscopic confirmation of the existence of low-mass quiescent galaxies at cosmic noon, showcasing the power of JWST to identify and characterize this enigmatic population.

astro-ph.GA↗

arXiv2022

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, the Euclidean information extracted from voxels can offer contextual cues representing interactions between nearby objects, while the geodesic information extracted from meshes can help separate objects that are spatially close but have disconnected surfaces. To incorporate such information from the two domains, we design an intra-domain attentive module for effective feature aggregation and an inter-domain attentive module for adaptive feature fusion. Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% vs 72.5% and 73.6% in mIoU) with a simpler network structure (17M vs 30M and 38M parameters). Code release: https://github.com/hzykent/VMNet

cs.CV↗

arXiv2022

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability

Although many methods have been proposed to enhance the transferability of adversarial perturbations, these methods are designed in a heuristic manner, and the essential mechanism for improving adversarial transferability is still unclear. This paper summarizes the common mechanism shared by twelve previous transferability-boosting methods in a unified view, i.e., these methods all reduce game-theoretic interactions between regional adversarial perturbations. To this end, we focus on the attacking utility of all interactions between regional adversarial perturbations, and we first discover and prove the negative correlation between the adversarial transferability and the attacking utility of interactions. Based on this discovery, we theoretically prove and empirically verify that twelve previous transferability-boosting methods all reduce interactions between regional adversarial perturbations. More crucially, we consider the reduction of interactions as the essential reason for the enhancement of adversarial transferability. Furthermore, we design the interaction loss to directly penalize interactions between regional adversarial perturbations during attacking. Experimental results show that the interaction loss significantly improves the transferability of adversarial perturbations.

cs.LG↗

arXiv2022

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solutions given a natural language problem description. We train PanGu-Coder using a two-stage strategy: the first stage employs Causal Language Modelling (CLM) to pre-train on raw programming language data, while the second stage uses a combination of Causal Language Modelling and Masked Language Modelling (MLM) training objectives that focus on the downstream task of text-to-code generation and train on loosely curated pairs of natural language program definitions and code functions. Finally, we discuss PanGu-Coder-FT, which is fine-tuned on a combination of competitive programming problems and code with continuous integration tests. We evaluate PanGu-Coder with a focus on whether it generates functionally correct programs and demonstrate that it achieves equivalent or better performance than similarly sized models, such as CodeX, while attending a smaller context window and training on less data.

cs.LG↗

arXiv2022

Neural-Sim: Learning to Generate Training Data with NeRF

Training computer vision models usually requires collecting and labeling vast amounts of imagery under a diverse set of scene configurations and properties. This process is incredibly time-consuming, and it is challenging to ensure that the captured data distribution maps well to the target domain of an application scenario. Recently, synthetic data has emerged as a way to address both of these issues. However, existing approaches either require human experts to manually tune each scene property or use automatic methods that provide little to no control; this requires rendering large amounts of random data variations, which is slow and is often suboptimal for the target domain. We present the first fully differentiable synthetic data pipeline that uses Neural Radiance Fields (NeRFs) in a closed-loop with a target application's loss function. Our approach generates data on-demand, with no human labor, to maximize accuracy for a target task. We illustrate the effectiveness of our method on synthetic and real-world object detection tasks. We also introduce a new "YCB-in-the-Wild" dataset and benchmark that provides a test scenario for object detection with varied poses in real-world environments.

cs.CV↗

arXiv2022

Scene Recognition with Objectness, Attribute and Category Learning

Scene classification has established itself as a challenging research problem. Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of granularity of recognition. Yet, image recognition serves as a key pillar for the good performance of scene recognition as the knowledge attained from object images can be used for accurate recognition of scenes. The existing scene recognition methods only take the category label of the scene into consideration. However, we find that the contextual information that contains detailed local descriptions are also beneficial in allowing the scene recognition model to be more discriminative. In this paper, we aim to improve scene recognition using attribute and category label information encoded in objects. Based on the complementarity of attribute and category labels, we propose a Multi-task Attribute-Scene Recognition (MASR) network which learns a category embedding and at the same time predicts scene attributes. Attribute acquisition and object annotation are tedious and time consuming tasks. We tackle the problem by proposing a partially supervised annotation strategy in which human intervention is significantly reduced. The strategy provides a much more cost-effective solution to real world scenarios, and requires considerably less annotation efforts. Moreover, we re-weight the attribute predictions considering the level of importance indicated by the object detected scores. Using the proposed method, we efficiently annotate attribute labels for four large-scale datasets, and systematically investigate how scene and attribute recognition benefit from each other. The experimental results demonstrate that MASR learns a more discriminative representation and achieves competitive recognition performance compared to the state-of-the-art methods

cs.CV↗

arXiv2022

Covering Grassmannian Codes: Bounds and Constructions

Grassmannian $\mathcal{G}_q(n,k)$ is the set of all $k$-dimensional subspaces of the vector space $\mathbb{F}_q^n.$ Recently, Etzion and Zhang introduced a new notion called covering Grassmannian code which can be used in network coding solutions for generalized combination networks. An $α$-$(n,k,δ)_q^c$ covering Grassmannian code $\mathcal{C}$ is a subset of $\mathcal{G}_q(n,k)$ such that every set of $α$ codewords of $\mathcal{C}$ spans a subspace of dimension at least $δ+k$ in $\mathbb{F}_q^n.$ In this paper, we derive new upper and lower bounds on the size of covering Grassmannian codes. These bounds improve and extend the parameter range of known bounds.

cs.IT↗

arXiv2022

ReFormer: The Relational Transformer for Image Captioning

Image captioning is shown to be able to achieve a better performance by using scene graphs to represent the relations of objects in the image. The current captioning encoders generally use a Graph Convolutional Net (GCN) to represent the relation information and merge it with the object region features via concatenation or convolution to get the final input for sentence decoding. However, the GCN-based encoders in the existing methods are less effective for captioning due to two reasons. First, using the image captioning as the objective (i.e., Maximum Likelihood Estimation) rather than a relation-centric loss cannot fully explore the potential of the encoder. Second, using a pre-trained model instead of the encoder itself to extract the relationships is not flexible and cannot contribute to the explainability of the model. To improve the quality of image captioning, we propose a novel architecture ReFormer -- a RElational transFORMER to generate features with relation information embedded and to explicitly express the pair-wise relationships between objects in the image. ReFormer incorporates the objective of scene graph generation with that of image captioning using one modified Transformer model. This design allows ReFormer to generate not only better image captions with the bene-fit of extracting strong relational image features, but also scene graphs to explicitly describe the pair-wise relation-ships. Experiments on publicly available datasets show that our model significantly outperforms state-of-the-art methods on image captioning and scene graph generation

cs.CV↗

arXiv2022

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available. Metalearning methods can address this problem by transferring knowledge from related tasks, thus reducing the amount of data and computing resources needed to learn new tasks. We organize the MetaDL competition series, which provide opportunities for research groups all over the world to create and experimentally assess new meta-(deep)learning solutions for real problems. In this paper, authored collaboratively between the competition organizers and the top-ranked participants, we describe the design of the competition, the datasets, the best experimental results, as well as the top-ranked methods in the NeurIPS 2021 challenge, which attracted 15 active teams who made it to the final phase (by outperforming the baseline), making over 100 code submissions during the feedback phase. The solutions of the top participants have been open-sourced. The lessons learned include that learning good representations is essential for effective transfer learning.

cs.LG↗

arXiv2022

Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization

Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks. However, these methods focus only on global distribution adaptation and ignore distribution constraints at the category level, which would lead to sub-optimal adaptation performance. This paper presents an unsupervised domain adaptation framework based on category-level regularization that regularizes the category distribution from three perspectives. Specifically, for inter-domain category regularization, an adaptive prototype alignment module is proposed to align feature prototypes of the same category in the source and target domains. In addition, for intra-domain category regularization, we tailored a regularization technique for the source and target domains, respectively. In the source domain, a prototype-guided discriminative loss is proposed to learn more discriminative feature representations by enforcing intra-class compactness and inter-class separability, and as a complement to traditional supervised loss. In the target domain, an augmented consistency category regularization loss is proposed to force the model to produce consistent predictions for augmented/unaugmented target images, which encourages semantically similar regions to be given the same label. Extensive experiments on two publicly fundus datasets show that the proposed approach significantly outperforms other state-of-the-art comparison algorithms.

cs.CV↗

arXiv2022

Enhanced brain structure-function tethering in transmodal cortex revealed by high-frequency eigenmodes

The brain's structural connectome supports signal propagation between neuronal elements, shaping diverse coactivation patterns that can be captured as functional connectivity. While the link between structure and function remains an ongoing challenge, the prevailing hypothesis is that the structure-function relationship may itself be gradually decoupled along a macroscale functional gradient spanning unimodal to transmodal regions. However, this hypothesis is strongly constrained by the underlying models which may neglect requisite signaling mechanisms. Here, we transform the structural connectome into a set of orthogonal eigenmodes governing frequency-specific diffusion patterns and show that regional structure-function relationships vary markedly under different signaling mechanisms. Specifically, low-frequency eigenmodes, which are considered sufficient to capture the essence of the functional network, contribute little to functional connectivity reconstruction in transmodal regions, resulting in structure-function decoupling along the unimodal-transmodal gradient. In contrast, high-frequency eigenmodes, which are usually on the periphery of attention due to their association with noisy and random dynamical patterns, contribute significantly to functional connectivity prediction in transmodal regions, inducing gradually convergent structure-function relationships from unimodal to transmodal regions. Although the information in high-frequency eigenmodes is weak and scattered, it effectively enhances the structure-function correspondence by 35% in unimodal regions and 56% in transmodal regions. Altogether, our findings suggest that the structure-function divergence in transmodal areas may not be an intrinsic property of brain organization, but can be narrowed through multiplexed and regionally specialized signaling mechanisms.

q-bio.NC↗

arXiv2022

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios. Moreover, the model can significantly reduce model size and power consumption without loss of quality. Namely, with the dynamic cascaded encoder model, we explore three techniques to maximally boost the performance of each model size: 1) Use separate decoders for each sub-model while sharing the encoders; 2) Use funnel-pooling to improve the encoder efficiency; 3) Balance the size of causal and non-causal encoders to improve quality and fit deployment constraints. Overall, the proposed large-medium model has 30% smaller size and reduces power consumption by 33%, compared to the baseline cascaded encoder model. The triple-size model that unifies the large, medium, and small models achieves 37% total size reduction with minimal quality loss, while substantially reducing the engineering efforts of having separate models.

eess.AS↗

arXiv2022

Concentration of Data Encoding in Parameterized Quantum Circuits

Variational quantum algorithms have been acknowledged as a leading strategy to realize near-term quantum advantages in meaningful tasks, including machine learning and combinatorial optimization. When applied to tasks involving classical data, such algorithms generally begin with quantum circuits for data encoding and then train quantum neural networks (QNNs) to minimize target functions. Although QNNs have been widely studied to improve these algorithms' performance on practical tasks, there is a gap in systematically understanding the influence of data encoding on the eventual performance. In this paper, we make progress in filling this gap by considering the common data encoding strategies based on parameterized quantum circuits. We prove that, under reasonable assumptions, the distance between the average encoded state and the maximally mixed state could be explicitly upper-bounded with respect to the width and depth of the encoding circuit. This result in particular implies that the average encoded state will concentrate on the maximally mixed state at an exponential speed on depth. Such concentration seriously limits the capabilities of quantum classifiers, and strictly restricts the distinguishability of encoded states from a quantum information perspective. We further support our findings by numerically verifying these results on both synthetic and public data sets. Our results highlight the significance of quantum data encoding in machine learning tasks and may shed light on future encoding strategies.

quant-ph↗

arXiv2022

Deep Learning-based Massive MIMO CSI Acquisition for 5G Evolution and 6G

Recently, inspired by successful applications in many fields, deep learning (DL) technologies for CSI acquisition have received considerable research interest from both academia and industry. Considering the practical feedback mechanism of 5th generation (5G) New radio (NR) networks, we propose two implementation schemes for artificial intelligence for CSI (AI4CSI), the DL-based receiver and end-to-end design, respectively. The proposed AI4CSI schemes were evaluated in 5G NR networks in terms of spectrum efficiency (SE), feedback overhead, and computational complexity, and compared with legacy schemes. To demonstrate whether these schemes can be used in real-life scenarios, both the modeled-based channel data and practically measured channels were used in our investigations. When DL-based CSI acquisition is applied to the receiver only, which has little air interface impact, it provides approximately 25\% SE gain at a moderate feedback overhead level. It is feasible to deploy it in current 5G networks during 5G evolutions. For the end-to-end DL-based CSI enhancements, the evaluations also demonstrated their additional performance gain on SE, which is 6% -- 26% compared with DL-based receivers and 33% -- 58% compared with legacy CSI schemes. Considering its large impact on air-interface design, it will be a candidate technology for 6th generation (6G) networks, in which an air interface designed by artificial intelligence can be used.

eess.SP↗

arXiv2022

A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions

Clustering is a fundamental machine learning task which has been widely studied in the literature. Classic clustering methods follow the assumption that data are represented as features in a vectorized form through various representation learning techniques. As the data become increasingly complicated and complex, the shallow (traditional) clustering methods can no longer handle the high-dimensional data type. With the huge success of deep learning, especially the deep unsupervised learning, many representation learning techniques with deep architectures have been proposed in the past decade. Recently, the concept of Deep Clustering, i.e., jointly optimizing the representation learning and clustering, has been proposed and hence attracted growing attention in the community. Motivated by the tremendous success of deep learning in clustering, one of the most fundamental machine learning tasks, and the large number of recent advances in this direction, in this paper we conduct a comprehensive survey on deep clustering by proposing a new taxonomy of different state-of-the-art approaches. We summarize the essential components of deep clustering and categorize existing methods by the ways they design interactions between deep representation learning and clustering. Moreover, this survey also provides the popular benchmark datasets, evaluation metrics and open-source implementations to clearly illustrate various experimental settings. Last but not least, we discuss the practical applications of deep clustering and suggest challenging topics deserving further investigations as future directions.

cs.LG↗

arXiv2022

Visual Attention Emerges from Recurrent Sparse Reconstruction

Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse reconstruction, a new attention formulation built on two prominent features of the human visual attention mechanism: recurrency and sparsity. Related features are grouped together via recurrent connections between neurons, with salient objects emerging via sparse regularization. VARS adopts an attractor network with recurrent connections that converges toward a stable pattern over time. Network layers are represented as ordinary differential equations (ODEs), formulating attention as a recurrent attractor network that equivalently optimizes the sparse reconstruction of input using a dictionary of "templates" encoding underlying patterns of data. We show that self-attention is a special case of VARS with a single-step optimization and no sparsity constraint. VARS can be readily used as a replacement for self-attention in popular vision transformers, consistently improving their robustness across various benchmarks. Code is released on GitHub (https://github.com/bfshi/VARS).

cs.CV↗