arXiv subjects

Rui Cao

Publications and source records attributed to Rui Cao.

At least 73 records · Page 4Linked to original sources

arXiv2023

A Refining Underlying Information Framework for Monaural Speech Enhancement

Supervised speech enhancement has gained significantly from recent advancements in neural networks, especially due to their ability to non-linearly fit the diverse representations of target speech, such as waveform or spectrum. However, these direct-fitting solutions continue to face challenges with degraded speech and residual noise in hearing evaluations. By bridging the speech enhancement and the Information Bottleneck principle in this letter, we rethink a universal plug-and-play strategy and propose a Refining Underlying Information framework called RUI to rise to the challenges both in theory and practice. Specifically, we first transform the objective of speech enhancement into an incremental convergence problem of mutual information between comprehensive speech characteristics and individual speech characteristics, e.g., spectral and acoustic characteristics. By doing so, compared with the existing direct-fitting solutions, the underlying information stems from the conditional entropy of acoustic characteristic given spectral characteristics. Therefore, we design a dual-path multiple refinement iterator based on the chain rule of entropy to refine this underlying information for further approximating target speech. Experimental results on DNS-Challenge dataset show that our solution consistently improves 0.3+ PESQ score over baselines, with only additional 1.18 M parameters. The source code is available at https://github.com/caoruitju/RUI_SE.

eess.AS↗

arXiv2023

MATK: The Meme Analytical Tool Kit

The rise of social media platforms has brought about a new digital culture called memes. Memes, which combine visuals and text, can strongly influence public opinions on social and cultural issues. As a result, people have become interested in categorizing memes, leading to the development of various datasets and multimodal models that show promising results in this field. However, there is currently a lack of a single library that allows for the reproduction, evaluation, and comparison of these models using fair benchmarks and settings. To fill this gap, we introduce the Meme Analytical Tool Kit (MATK), an open-source toolkit specifically designed to support existing memes datasets and cutting-edge multimodal models. MATK aims to assist researchers and engineers in training and reproducing these multimodal models for meme classification tasks, while also providing analysis techniques to gain insights into their strengths and weaknesses. To access MATK, please visit \url{https://github.com/Social-AI-Studio/MATK}.

cs.CL↗

arXiv2023

Empirical Review of Smart Contract and DeFi Security: Vulnerability Detection and Automated Repair

Decentralized Finance (DeFi) is emerging as a peer-to-peer financial ecosystem, enabling participants to trade products on a permissionless blockchain. Built on blockchain and smart contracts, the DeFi ecosystem has experienced explosive growth in recent years. Unfortunately, smart contracts hold a massive amount of value, making them an attractive target for attacks. So far, attacks against smart contracts and DeFi protocols have resulted in billions of dollars in financial losses, severely threatening the security of the entire DeFi ecosystem. Researchers have proposed various security tools for smart contracts and DeFi protocols as countermeasures. However, a comprehensive investigation of these efforts is still lacking, leaving a crucial gap in our understanding of how to enhance the security posture of the smart contract and DeFi landscape. To fill the gap, this paper reviews the progress made in the field of smart contract and DeFi security from the perspective of both vulnerability detection and automated repair. First, we analyze the DeFi smart contract security issues and challenges. Specifically, we lucubrate various DeFi attack incidents and summarize the attacks into six categories. Then, we present an empirical study of 42 state-of-the-art techniques that can detect smart contract and DeFi vulnerabilities. In particular, we evaluate the effectiveness of traditional smart contract bug detection tools in analyzing complex DeFi protocols. Additionally, we investigate 8 existing automated repair tools for smart contracts and DeFi protocols, providing insight into their advantages and disadvantages. To make this work useful for as wide of an audience as possible, we also identify several open issues and challenges in the DeFi ecosystem that should be addressed in the future.

cs.CR↗

arXiv2023

Responsible Urban Intelligence: Towards a Research Agenda

Acceleration of urbanisation is posing great challenges to sustainable development. Growing accessibility to big data and artificial intelligence (AI) technologies have revolutionised many fields and offered great potential for addressing pressing urban problems. However, using these technologies without explicitly considering responsibilities would bring new societal and environmental issues. To maximise the benefits of big data and AI while minimising potential issues, we envisage a conceptual framework of Responsible Urban Intelligence (RUI) and advocate an agenda for action. We first define RUI as consisting of three major components including urban problems, enabling technologies, and responsibilities; then introduce transparency, fairness, and eco-friendliness as the three dimensions of responsibilities which naturally link with the human, space, and time dimensions of cities; and further develop a four-stage implementation framework for responsibilities as consisting of solution design, data preparation, model building, and practical application; and finally present a research agenda for RUI addressing challenging issues including data and model transparency, tension between performance and fairness, and solving urban problems in an eco-friendly manner.

cs.CY↗

arXiv2023

Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection

Hateful meme detection is a challenging multimodal task that requires comprehension of both vision and language, as well as cross-modal interactions. Recent studies have tried to fine-tune pre-trained vision-language models (PVLMs) for this task. However, with increasing model sizes, it becomes important to leverage powerful PVLMs more efficiently, rather than simply fine-tuning them. Recently, researchers have attempted to convert meme images into textual captions and prompt language models for predictions. This approach has shown good performance but suffers from non-informative image captions. Considering the two factors mentioned above, we propose a probing-based captioning approach to leverage PVLMs in a zero-shot visual question answering (VQA) manner. Specifically, we prompt a frozen PVLM by asking hateful content-related questions and use the answers as image captions (which we call Pro-Cap), so that the captions contain information critical for hateful content detection. The good performance of models with Pro-Cap on three benchmarks validates the effectiveness and generalization of the proposed method.

cs.CV↗

arXiv2023

Broadband Digital Over-the-Air Computation for Wireless Federated Edge Learning

This paper presents the first orthogonal frequency-division multiplexing(OFDM)-based digital over-the-air computation (AirComp) system for wireless federated edge learning, where multiple edge devices transmit model data simultaneously using non-orthogonal OFDM subcarriers, and the edge server aggregates data directly from the superimposed signal. Existing analog AirComp systems often assume perfect phase alignment via channel precoding and utilize uncoded analog transmission for model aggregation. In contrast, our digital AirComp system leverages digital modulation and channel codes to overcome phase asynchrony, thereby achieving accurate model aggregation for phase-asynchronous multi-user OFDM systems. To realize a digital AirComp system, we develop a medium access control (MAC) protocol that allows simultaneous transmissions from different users using non-orthogonal OFDM subcarriers, and put forth joint channel decoding and aggregation decoders tailored for convolutional and LDPC codes. To verify the proposed system design, we build a digital AirComp prototype on the USRP software-defined radio platform, and demonstrate a real-time LDPC-coded AirComp system with up to four users. Trace-driven simulation results on test accuracy versus SNR show that: 1) analog AirComp is sensitive to phase asynchrony in practical multi-user OFDM systems, and the test accuracy performance fails to improve even at high SNRs; 2) our digital AirComp system outperforms two analog AirComp systems at all SNRs, and approaches the optimal performance when SNR $\geq$ 6 dB for two-user LDPC-coded AirComp, demonstrating the advantage of digital AirComp in phase-asynchronous multi-user OFDM systems.

cs.IT↗

arXiv2023

Single-shot 3D photoacoustic computed tomography with a densely packed array for transcranial functional imaging

Photoacoustic computed tomography (PACT) is emerging as a new technique for functional brain imaging, primarily due to its capabilities in label-free hemodynamic imaging. Despite its potential, the transcranial application of PACT has encountered hurdles, such as acoustic attenuations and distortions by the skull and limited light penetration through the skull. To overcome these challenges, we have engineered a PACT system that features a densely packed hemispherical ultrasonic transducer array with 3072 channels, operating at a central frequency of 1 MHz. This system allows for single-shot 3D imaging at a rate equal to the laser repetition rate, such as 20 Hz. We have achieved a single-shot light penetration depth of approximately 9 cm in chicken breast tissue utilizing a 750 nm laser (withstanding 3295-fold light attenuation and still retaining an SNR of 74) and successfully performed transcranial imaging through an ex vivo human skull using a 1064 nm laser. Moreover, we have proven the capacity of our system to perform single-shot 3D PACT imaging in both tissue phantoms and human subjects. These results suggest that our PACT system is poised to unlock potential for real-time, in vivo transcranial functional imaging in humans.

physics.med-ph↗

arXiv2023

Rethinking the visual cues in audio-visual speaker extraction

The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual front-end in AVSE is often derived from a pre-trained model or end-to-end trained, making it unclear which visual cue contributes more to the speaker extraction performance. This raises the question of how to better utilize visual cues. To address this issue, we propose two training strategies that decouple the learning of the two visual cues. Our experimental results demonstrate that both visual cues are useful, with the synchronization cue having a higher impact. We introduce a more explainable model, the Decoupled Audio-Visual Speaker Extraction (DAVSE) model, which leverages both visual cues.

cs.SD↗

arXiv2023

Two-Stage Grasping: A New Bin Picking Framework for Small Objects

This paper proposes a novel bin picking framework, two-stage grasping, aiming at precise grasping of cluttered small objects. Object density estimation and rough grasping are conducted in the first stage. Fine segmentation, detection, grasping, and pushing are performed in the second stage. A small object bin picking system has been realized to exhibit the concept of two-stage grasping. Experiments have shown the effectiveness of the proposed framework. Unlike traditional bin picking methods focusing on vision-based grasping planning using classic frameworks, the challenges of picking cluttered small objects can be solved by the proposed new framework with simple vision detection and planning.

cs.RO↗

arXiv2023

Quantum imaging of biological organisms through spatial and polarization entanglement

Quantum imaging can potentially provide certain advantages over classical imaging. Thus far, however, the signal-to-noise ratios (SNRs) are poor; the resolvable pixel counts are low; biological organisms have not been imaged; birefringence has not been quantified. Here, we introduce quantum imaging by coincidence from entanglement (ICE). Utilizing spatially and polarization entangled photon pairs, ICE exhibits higher SNRs, greater resolvable pixel counts, imaging of biological organisms, and ghost birefringence quantification; it also enables 25 times greater suppression of stray light than classical imaging. ICE can potentially empower quantum imaging towards new applications in life sciences and remote sensing.

quant-ph↗

arXiv2023

Prompting for Multimodal Hateful Meme Classification

Hateful meme classification is a challenging multimodal task that requires complex reasoning and contextual background knowledge. Ideally, we could leverage an explicit external knowledge base to supplement contextual and cultural information in hateful memes. However, there is no known explicit external knowledge base that could provide such hate speech contextual information. To address this gap, we propose PromptHate, a simple yet effective prompt-based model that prompts pre-trained language models (PLMs) for hateful meme classification. Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pre-trained RoBERTa language model for hateful meme classification. We conduct extensive experiments on two publicly available hateful and offensive meme datasets. Our experimental results show that PromptHate is able to achieve a high AUC of 90.96, outperforming state-of-the-art baselines on the hateful meme classification task. We also perform fine-grained analyses and case studies on various prompt settings and demonstrate the effectiveness of the prompts on hateful meme classification.

cs.CL↗

arXiv2022

Emergent Orbital Skyrmion Lattice in a Triangular Atom Array

Multi-orbital optical lattices have been attracting rapidly growing research interests in the last several years, providing fascinating opportunities for orbital-based quantum simulations. Here, we consider bosonic atoms loaded in the degenerate $p$-orbital bands of a two-dimensional triangular optical lattice. This system is described by a multi-orbital Bose-Hubbard model. We find the confined atoms in this system develop spontaneous orbital polarization, which forms a chiral Skyrmion lattice pattern in a large regime of the phase diagram. This is in contrast to its spin analogue which largely requires spin-orbit couplings. The emergence of the Skyrmion lattice is confirmed in both bosonic dynamical mean-field theory (BDMFT) and exact diagonalization (ED) calculations. By analyzing the quantum tunneling induced orbital-exchange interaction in the strong interaction limit, we find the Skyrmion lattice state arises due to the interplay of $p$-orbital symmetry and the geometric frustration of the triangular lattice. We provide experimental consequences of the orbital Skyrmion state, that can be readily tested in cold atom experiments. Our study implies orbital-based quantum simulations could bring exotic scenarios unexpected from their spin analogue.

cond-mat.quant-gas↗

arXiv2022

A Coarse-to-Fine Approach for Urban Land Use Mapping Based on Multisource Geospatial Data

Timely and accurate land use mapping is a long-standing problem, which is critical for effective land and space planning and management. Due to complex and mixed use, it is challenging for accurate land use mapping from widely-used remote sensing images (RSI) directly, especially for high-density cities. To address this issue, in this paper, we propose a coarse-to-fine machine learning-based approach for parcel-level urban land use mapping, integrating multisource geospatial data, including RSI, points-of-interest (POI), and area-of-interest (AOI) data. Specifically, we first divide the city into built-up and non-built-up regions based on parcels generated from road networks. Then, we adopt different classification strategies for parcels in different regions, and finally combine the classified results into an integrated land use map. The results show that the proposed approach can significantly outperform baseline method that mixes built-up and non-built-up regions, with accuracy increase of 25% and 30% for level-1 and level-2 classification, respectively. In addition, we examine the rarely explored AOI data, which can further boost the level-1 and level-2 classification accuracy by 13% and 14%. These results demonstrate the effectiveness of the proposed approach and also indicate the usefulness of AOIs for land use mapping, which are valuable for further studies.

cs.CV↗

arXiv2022

Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking

In this paper, we propose an iterative self-training framework for sim-to-real 6D object pose estimation to facilitate cost-effective robotic grasping. Given a bin-picking scenario, we establish a photo-realistic simulator to synthesize abundant virtual data, and use this to train an initial pose estimation network. This network then takes the role of a teacher model, which generates pose predictions for unlabeled real data. With these predictions, we further design a comprehensive adaptive selection scheme to distinguish reliable results, and leverage them as pseudo labels to update a student model for pose estimation on real data. To continuously improve the quality of pseudo labels, we iterate the above steps by taking the trained student model as a new teacher and re-label real data using the refined teacher model. We evaluate our method on a public benchmark and our newly-released dataset, achieving an ADD(-S) improvement of 11.49% and 22.62% respectively. Our method is also able to improve robotic bin-picking success by 19.54%, demonstrating the potential of iterative sim-to-real solutions for robotic applications.

cs.RO↗

arXiv2022

Quantum phases of spin-orbital-angular-momentum coupled bosonic gases in optical lattices

Spin-orbit coupling plays an important role in understanding exotic quantum phases. In this work, we present a scheme to combine spin-orbital-angular-momentum (SOAM) coupling and strong correlations in ultracold atomic gases. Essential ingredients of this setting is the interplay of SOAM coupling and Raman-induced spin-flip hopping, engineered by lasers that couples different hyperfine spin states. In the presence of SOAM coupling only, we find rich quantum phases in the Mott-insulating regime, which support different types of spin defects such as spin vortex and composite vortex with antiferromagnetic core surrounded by the outer spin vortex. Based on an effective exchange model, we find that these competing spin textures are a result of the interplay of Dzyaloshinskii-Moriya and Heisenberg exchange interactions. In the presence of both SOAM coupling and Raman-induced spin-flip hopping, more many-body phases appear, including canted-antiferromagnetic and stripe phases. Our prediction suggests that SOAM coupling could induce rich exotic many-body phases in the strongly interacting regime.

cond-mat.quant-gas↗

arXiv2022

Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding

Contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. This technique requires a balanced mixture of two ingredients: positive (similar) and negative (dissimilar) samples. This is typically achieved by maintaining a queue of negative samples during training. Prior works in the area typically uses a fixed-length negative sample queue, but how the negative sample size affects the model performance remains unclear. The opaque impact of the number of negative samples on performance when employing contrastive learning aroused our in-depth exploration. This paper presents a momentum contrastive learning model with negative sample queue for sentence embedding, namely MoCoSE. We add the prediction layer to the online branch to make the model asymmetric and together with EMA update mechanism of the target branch to prevent the model from collapsing. We define a maximum traceable distance metric, through which we learn to what extent the text contrastive learning benefits from the historical information of negative samples. Our experiments find that the best results are obtained when the maximum traceable distance is at a certain range, demonstrating that there is an optimal range of historical information for a negative sample queue. We evaluate the proposed unsupervised MoCoSE on the semantic text similarity (STS) task and obtain an average Spearman's correlation of $77.27\%$. Source code is available at https://github.com/xbdxwyh/mocose.

cs.CL↗

arXiv2022

Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking

Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances. Particularly, industrial objects can have irregular shapes, that is, thin and concave, whereas in bin-picking scenarios, objects are often closely packed with strong occlusion. To address these challenges, we formulate a novel part-aware instance segmentation pipeline. The key idea is to decompose industrial objects into correlated approximate convex parts and enhance the object-level segmentation with part-level segmentation. We design a part-aware network to predict part masks and part-to-part offsets, followed by a part aggregation module to assemble the recognized parts into instances. To guide the network learning, we also propose an automatic label decoupling scheme to generate ground-truth part-level labels from instance-level labels. Finally, we contribute the first instance segmentation dataset, which contains a variety of industrial objects that are thin and have non-trivial shapes. Extensive experimental results on various industrial objects demonstrate that our method can achieve the best segmentation results compared with the state-of-the-art approaches.

cs.CV↗

arXiv2021

Broadband Digital Over-the-Air Computation for Asynchronous Federated Edge Learning

This paper presents the first broadband digital over-the-air computation (AirComp) system for phase asynchronous OFDM-based federated edge learning systems. Existing analog AirComp systems often assume perfect phase alignment via channel precoding and utilize uncoded analog modulation for model aggregation. In contrast, our digital AirComp system leverages digital modulation and channel codes to overcome phase asynchrony, thereby achieving accurate model aggregation in the asynchronous multi-user OFDM systems. To realize a digital AirComp system, we propose a non-orthogonal multiple access protocol that allows simultaneous transmissions from multiple edge devices, and present a joint channel decoding and aggregation (Jt-CDA) decoder (i.e., full-state joint decoder). To reduce the computation complexity, we further present a reduced-complexity Jt-CDA decoder (i.e., reduced-state joint decoder), and its arithmetic sum bit error rate performance is similar to that of the full-state joint decoder for most signal-to-noise ratio (SNR) regimes. Simulation results on test accuracy (of CIFAR10 dataset) versus SNR show that: 1) analog AirComp systems are sensitive to phase asynchrony under practical setup, and the test accuracy performance exhibits an error floor even at high SNR regime; 2) our digital AirComp system outperforms an analog AirComp system by at least 1.5 times when SNR 9dB, demonstrating the advantage of digital AirComp in asynchronous multi-user OFDM systems.

cs.IT↗