arXiv subjects

Lin Zhang

Publications and source records attributed to Lin Zhang.

At least 235 records · Page 13Linked to original sources

arXiv2023

LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such training-testing mismatch is the absence of publicly available multi-reference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112,142 groups of 300x300 training images, which is 10x of the existing largest RefSR dataset. The image size is also much larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multi-reference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and data would be made available soon.

cs.CV↗

arXiv2023

Dynamical detection of mean-field topological phases in an interacting Chern insulator

Interactions generically have important effects on the topological quantum phases. For a quantum anomalous Hall (QAH) insulator, the presence of interactions can qualitatively change the topological phase diagram which, however, is typically hard to measure in the experiment. Here we propose a novel scheme based on quench dynamics to detect the mean-field topological phase diagram of an interacting Chern insulator described by QAH-Hubbard model, with nontrivial dynamical quantum physics being uncovered. We focus on the dynamical properties of the system at a weak to intermediate Hubbard interaction which mainly induces a ferromagnetic order under the mean-field level. Remarkably, three characteristic times $t_s$, $t_c$, and $t^*$ are found in the quench dynamics. The first two capture the emergence of dynamical self-consistent particle density and dynamical topological phase transition respectively, while the last one gives a linear scaling time on the topological phase boundaries. A more interesting result is that $t_s>t^*>t_c$ ($t^*<t_s<t_c$) occurs in repulsive (attractive) interaction and the Chern number is determined by any two characteristic time scales when the system is quenched from an initial nearly fully polarized state to the topologically nontrivial regimes, showing a dynamical way to determine equilibrium mean-field topological phase diagram via the time scales. Experimentally,the measurement of $t_s$ is challenging while $t_c$ and $t^*$ can be directly readout by measuring the spin polarizations of four Dirac points and the time-dependent particle density, respectively. Our work reveals the novel interacting effects on the topological phases and shall promote the experimental observation.

cond-mat.str-el↗

arXiv2023

Artificial Intelligence: 70 Years Down the Road

Artificial intelligence (AI) has a history of nearly a century from its inception to the present day. We have summarized the development trends and discovered universal rules, including both success and failure. We have analyzed the reasons from both technical and philosophical perspectives to help understand the reasons behind the past failures and current successes of AI, and to provide a basis for thinking and exploring future development. Specifically, we have found that the development of AI in different fields, including computer vision, natural language processing, and machine learning, follows a pattern from rules to statistics to data-driven methods. In the face of past failures and current successes, we need to think systematically about the reasons behind them. Given the unity of AI between natural and social sciences, it is necessary to incorporate philosophical thinking to understand and solve AI problems, and we believe that starting from the dialectical method of Marx is a feasible path. We have concluded that the sustainable development direction of AI should be human-machine collaboration and a technology path centered on computing power. Finally, we have summarized the impact of AI on society from this trend.

cs.AI↗

arXiv2023

Unpaired Translation from Semantic Label Maps to Images by Leveraging Domain-Specific Simulations

Photorealistic image generation from simulated label maps are necessitated in several contexts, such as for medical training in virtual reality. With conventional deep learning methods, this task requires images that are paired with semantic annotations, which typically are unavailable. We introduce a contrastive learning framework for generating photorealistic images from simulated label maps, by learning from unpaired sets of both. Due to potentially large scene differences between real images and label maps, existing unpaired image translation methods lead to artifacts of scene modification in synthesized images. We utilize simulated images as surrogate targets for a contrastive loss, while ensuring consistency by utilizing features from a reverse translation network. Our method enables bidirectional label-image translations, which is demonstrated in a variety of scenarios and datasets, including laparoscopy, ultrasound, and driving scenes. By comparing with state-of-the-art unpaired translation methods, our proposed method is shown to generate realistic and scene-accurate translations.

cs.CV↗

arXiv2023

Steady-state Peierls transition in nanotube quantum simulator

Quantum dots placed along a vibrating nanotube provide a quantum simulation platform that can directly address the electron-phonon interaction. This offers promising prospects for the search of new quantum materials and the study of strong correlation effects. As this platform is naturally operated by coupling the dots to an electronic reservoir, state preparation is straightforwardly achieved by driving into the steady state. Here we show that for intermediate electron-phonon coupling strength, the system with spin-polarized quantum dots undergoes a Peierls transition into an insulating regime which exhibits charge-density wave order in the steady state as a consequence of the competition between electronic Coulomb repulsive interactions and phonon-induced attractive interactions. The transport phenomena can be directly observed as fingerprints of electronic correlations. We also present powerful methods to numerically capture the physics of such an open electron-phonon system at large numbers of phonons. Our work paves the way to study and detect correlated electron-phonon physics in the nanotube quantum simulator with current experimentally accessible techniques.

cond-mat.str-el↗

arXiv2023

The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance

Automatic speaker verification is susceptible to various manipulations and spoofing, such as text-to-speech synthesis, voice conversion, replay, tampering, adversarial attacks, and so on. We consider a new spoofing scenario called "Partial Spoof" (PS) in which synthesized or transformed speech segments are embedded into a bona fide utterance. While existing countermeasures (CMs) can detect fully spoofed utterances, there is a need for their adaptation or extension to the PS scenario. We propose various improvements to construct a significantly more accurate CM that can detect and locate short-generated spoofed speech segments at finer temporal resolutions. First, we introduce newly developed self-supervised pre-trained models as enhanced feature extractors. Second, we extend our PartialSpoof database by adding segment labels for various temporal resolutions. Since the short spoofed speech segments to be embedded by attackers are of variable length, six different temporal resolutions are considered, ranging from as short as 20 ms to as large as 640 ms. Third, we propose a new CM that enables the simultaneous use of the segment-level labels at different temporal resolutions as well as utterance-level labels to execute utterance- and segment-level detection at the same time. We also show that the proposed CM is capable of detecting spoofing at the utterance level with low error rates in the PS scenario as well as in a related logical access (LA) scenario. The equal error rates of utterance-level detection on the PartialSpoof database and ASVspoof 2019 LA database were 0.77 and 0.90%, respectively.

eess.AS↗

arXiv2022

Unsupervised Instance and Subnetwork Selection for Network Data

Unlike tabular data, features in network data are interconnected within a domain-specific graph. Examples of this setting include gene expression overlaid on a protein interaction network (PPI) and user opinions in a social network. Network data is typically high-dimensional (large number of nodes) and often contains outlier snapshot instances and noise. In addition, it is often non-trivial and time-consuming to annotate instances with global labels (e.g., disease or normal). How can we jointly select discriminative subnetworks and representative instances for network data without supervision? We address these challenges within an unsupervised framework for joint subnetwork and instance selection in network data, called UISS, via a convex self-representation objective. Given an unlabeled network dataset, UISS identifies representative instances while ignoring outliers. It outperforms state-of-the-art baselines on both discriminative subnetwork selection and representative instance selection, achieving up to 10% accuracy improvement on all real-world data sets we use for evaluation. When employed for exploratory analysis in RNA-seq network samples from multiple studies it produces interpretable and informative summaries.

cs.LG↗

arXiv2022

A Large-scale Friend Suggestion Architecture

Online social as an extension of traditional life plays an important role in our daily lives. Users often seek out new friends that have significant similarities such as interests and habits, motivating us to exploit such online information to suggest friends to users. In this work, we focus on friend suggestion in online game platforms because in-game social quality significantly correlates with player engagement, determining game experience. Unlike a typical recommendation system that depends on item-user interactions, in our setting, user-user interactions do not depend on each other. Meanwhile, user preferences change rapidly due to fast changing game environment. There has been little work on designing friend suggestion when facing these difficulties, and for the first time we aim to tackle this in large scale online games. Motivated by the fast changing online game environment, we formulate this problem as friend ranking by modeling the evolution of similarity among users, exploiting the long-term and short-term feature of users in games. Our experiments on large-scale game datasets with several million users demonstrate that our proposed model achieves superior performance over other competing baselines.

cs.SI↗

arXiv2022

BEATS: An Open-Source, High-Precision, Multi-Channel EEG Acquisition Tool System

Stable and accurate electroencephalogram (EEG) signal acquisition is fundamental in non-invasive brain-computer interface (BCI) technology. Commonly used EEG acquisition system's hardware and software are usually closed-source. Its inability to flexible expansion and secondary development is a major obstacle to real-time BCI research. This paper presents the Beijing University of Posts and Telecommunications EEG Acquisition Tool System named BEATS. It implements a comprehensive system from hardware to software, composed of the analog front-end, microprocessor, and software platform. BEATS is capable of collecting 32-channel EEG signals at a guaranteed sampling rate of 4k Hz with wireless transmission. Compared to state-of-the-art systems used in many EEG fields, it displays a better sampling rate. Using techniques including direct memory access, first in first out, and timer, the precision and stability of the acquisition are ensured at the microsecond level. An evaluation is conducted during 24 hours of continuous acquisitions. The data loss is 0 packets and the average maximum delay is only 0.07 s/h. Moreover, as an open source system, BEATS provides detailed design files, and adopts a plug-in structure and easy-to-access materials, which makes it can be quickly reproduced. Schematics, source code, and other materials of BEATS are available at https://github.com/buptantEEG/BEATS.

eess.SP↗

arXiv2022

An Information-Theoretic Approach to Transferability in Task Transfer Learning

Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task. Typically, transferability is either measured experimentally or inferred through task relatedness, which is often defined without a clear operational meaning. In this paper, we present a novel metric, H-score, an easily-computable evaluation function that estimates the performance of transferred representations from one task to another in classification problems using statistical and information theoretic principles. Experiments on real image data show that our metric is not only consistent with the empirical transferability measurement, but also useful to practitioners in applications such as source model selection and task transfer curriculum learning.

cs.LG↗

arXiv2022

SsciBERT: A Pre-trained Language Model for Social Science Texts

The academic literature of social sciences records human civilization and studies human social problems. With its large-scale growth, the ways to quickly find existing research on relevant issues have become an urgent demand for researchers. Previous studies, such as SciBERT, have shown that pre-training using domain-specific texts can improve the performance of natural language processing tasks. However, the pre-trained language model for social sciences is not available so far. In light of this, the present research proposes a pre-trained model based on the abstracts published in the Social Science Citation Index (SSCI) journals. The models, which are available on GitHub (https://github.com/S-T-Full-Text-Knowledge-Mining/SSCI-BERT), show excellent performance on discipline classification, abstract structure-function recognition, and named entity recognition tasks with the social sciences literature.

cs.CL↗

arXiv2022

RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection

Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed SR image should enable better SR reconstruction for its similar LR images when it is referred to as. Therefore, in this work, we propose a reciprocal learning framework that can appropriately leverage such a fact to reinforce the learning of a RefSR network. Besides, we deliberately design a progressive feature alignment and selection module for further improving the RefSR task. The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection in a progressive manner, thus more precise reference features can be transferred into the input features and the network capability is enhanced. Our reciprocal learning paradigm is model-agnostic and it can be applied to arbitrary RefSR models. We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm. Furthermore, our proposed model together with the reciprocal learning strategy sets new state-of-the-art performances on multiple benchmarks.

cs.CV↗

arXiv2022

An Opponent-Aware Reinforcement Learning Method for Team-to-Team Multi-Vehicle Pursuit via Maximizing Mutual Information Indicator

The pursuit-evasion game in Smart City brings a profound impact on the Multi-vehicle Pursuit (MVP) problem, when police cars cooperatively pursue suspected vehicles. Existing studies on the MVP problems tend to set evading vehicles to move randomly or in a fixed prescribed route. The opponent modeling method has proven considerable promise in tackling the non-stationary caused by the adversary agent. However, most of them focus on two-player competitive games and easy scenarios without the interference of environments. This paper considers a Team-to-Team Multi-vehicle Pursuit (T2TMVP) problem in the complicated urban traffic scene where the evading vehicles adopt the pre-trained dynamic strategies to execute decisions intelligently. To solve this problem, we propose an opponent-aware reinforcement learning via maximizing mutual information indicator (OARLM2I2) method to improve pursuit efficiency in the complicated environment. First, a sequential encoding-based opponents joint strategy modeling (SEOJSM) mechanism is proposed to generate evading vehicles' joint strategy model, which assists the multi-agent decision-making process based on deep Q-network (DQN). Then, we design a mutual information-united loss, simultaneously considering the reward fed back from the environment and the effectiveness of opponents' joint strategy model, to update pursuing vehicles' decision-making process. Extensive experiments based on SUMO demonstrate our method outperforms other baselines by 21.48% on average in reducing pursuit time. The code is available at \url{https://github.com/ANT-ITS/OARLM2I2}.

cs.MA↗

arXiv2022

Graded-Q Reinforcement Learning with Information-Enhanced State Encoder for Hierarchical Collaborative Multi-Vehicle Pursuit

The multi-vehicle pursuit (MVP), as a problem abstracted from various real-world scenarios, is becoming a hot research topic in Intelligent Transportation System (ITS). The combination of Artificial Intelligence (AI) and connected vehicles has greatly promoted the research development of MVP. However, existing works on MVP pay little attention to the importance of information exchange and cooperation among pursuing vehicles under the complex urban traffic environment. This paper proposed a graded-Q reinforcement learning with information-enhanced state encoder (GQRL-IESE) framework to address this hierarchical collaborative multi-vehicle pursuit (HCMVP) problem. In the GQRL-IESE, a cooperative graded Q scheme is proposed to facilitate the decision-making of pursuing vehicles to improve pursuing efficiency. Each pursuing vehicle further uses a deep Q network (DQN) to make decisions based on its encoded state. A coordinated Q optimizing network adjusts the individual decisions based on the current environment traffic information to obtain the global optimal action set. In addition, an information-enhanced state encoder is designed to extract critical information from multiple perspectives and uses the attention mechanism to assist each pursuing vehicle in effectively determining the target. Extensive experimental results based on SUMO indicate that the total timestep of the proposed GQRL-IESE is less than other methods on average by 47.64%, which demonstrates the excellent pursuing efficiency of the GQRL-IESE. Codes are outsourced in https://github.com/ANT-ITS/GQRL-IESE.

cs.LG↗

arXiv2022

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective

We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and sentiment analysis. Zero-shot learning aims to train a model on a given task such that it can address new learning tasks without any additional training. Our approach converts zero-shot learning into multiple-choice tasks, avoiding problems in commonly used large-scale generative models such as FLAN. It not only adds generalization ability to models but also significantly reduces the number of parameters. Our method shares the merits of efficient training and deployment. Our approach shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as natural language inference and text classification. Our model achieves this success with only 235M parameters, which is substantially smaller than state-of-the-art models with billions of parameters. The code and pre-trained models are available at https://github.com/IDEA-CCNL/Fengshenbang-LM .

cs.CL↗

arXiv2022

Deep Spectro-temporal Artifacts for Detecting Synthesized Speech

The Audio Deep Synthesis Detection (ADD) Challenge has been held to detect generated human-like speech. With our submitted system, this paper provides an overall assessment of track 1 (Low-quality Fake Audio Detection) and track 2 (Partially Fake Audio Detection). In this paper, spectro-temporal artifacts were detected using raw temporal signals, spectral features, as well as deep embedding features. To address track 1, low-quality data augmentation, domain adaptation via finetuning, and various complementary feature information fusion were aggregated in our system. Furthermore, we analyzed the clustering characteristics of subsystems with different features by visualization method and explained the effectiveness of our proposed greedy fusion strategy. As for track 2, frame transition and smoothing were detected using self-supervised learning structure to capture the manipulation of PF attacks in the time domain. We ranked 4th and 5th in track 1 and track 2, respectively.

cs.SD↗

arXiv2022

Holographic cold dense matter constrained by neutron stars

The equation of state (EoS) for cold dense matter inside neutron stars is investigated by using holographic QCD models in the framework of the Einstein-Maxwell-dilaton (EMD) system and the improved Karch-Katz-Son-Stephanov (KKSS) action for matter part. This method of describing holographic nuclear matter in the EMD$+$KKSS framework is different from that by using the Dirac-Born-Infeld (DBI) action and the Chern-Simons (CS) terms. Combining with the Hebeler-Lattimer-Pethick-Schwenk (HLPS) intermediate equation of state (EoS), the hybrid EoS inside the neutron stars is constructed. The obtained hybrid EoS is located in the range that is defined by the low-density chiral effective theory, the high-density perturbative QCD, and the polytropic interpolations between them, and is constrained by the astrophysics observations. The square of the sound velocity reaches a maximum value larger than $0.8$ in the region of $2-5$ times the saturation baryon number density and approaches the conformal limit at the high baryon density range. The mass-radius relation and the tidal deformability of the neutron stars are in agreement with astrophysical measurements. The possible maximum mass for the neutron star is about $2.5 M_{\odot}$ and the radius is about $12 \mathrm{km}$ then. It is noticed that the holographic quark matter branch in the mass-radius relation is always unstable and the holographic nuclear matter can produce a stable branch. These results indicate that even in the core of the NS, the matter is still in the confinement phase and the quark matter is not favored.

nucl-th↗

arXiv2022

Spoofing-Aware Attention based ASV Back-end with Multiple Enrollment Utterances and a Sampling Strategy for the SASV Challenge 2022

Current state-of-the-art automatic speaker verification (ASV) systems are vulnerable to presentation attacks, and several countermeasures (CMs), which distinguish bona fide trials from spoofing ones, have been explored to protect ASV. However, ASV systems and CMs are generally developed and optimized independently without considering their inter-relationship. In this paper, we propose a new spoofing-aware ASV back-end module that efficiently computes a combined ASV score based on speaker similarity and CM score. In addition to the learnable fusion function of the two scores, the proposed back-end module has two types of attention components, scaled-dot and feed-forward self-attention, so that intra-relationship information of multiple enrollment utterances can also be learned at the same time. Moreover, a new effective trials-sampling strategy is designed for simulating new spoofing-aware verification scenarios introduced in the Spoof-Aware Speaker Verification (SASV) challenge 2022.

eess.AS↗