arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 757 records · Page 42Linked to original sources

arXiv2022

Iterative time-domain method for resolving multiple gravitational wave sources in Pulsar Timing Array data

The sensitivity of ongoing searches for gravitational wave (GW) sources in the ultra-low frequency regime ($10^{-9}$ Hz to $10^{-7}$ Hz) using Pulsar Timing Arrays (PTAs) will continue to increase in the future as more well-timed pulsars are added to the arrays. It is expected that next-generation radio telescopes, namely, the Five-hundred-meter Aperture Spherical radio Telescope (FAST) and the Square Kilometer Array (SKA), will grow the number of well-timed pulsars to $O(10^3)$. The higher sensitivity will result in greater distance reach for GW sources, uncovering multiple resolvable GW sources in addition to an unresolved population. Data analysis techniques are, therefore, required that can search for and resolve multiple signals present simultaneously in PTA data. The multisource resolution problem in PTA data analysis poses a unique set of challenges such as non-uniformly sampled data, a large number of so-called pulsar phase parameters that arise from the inaccurately measured distances to the pulsars, and poor separation of signals in the Fourier domain due to a small number of cycles in the observed waveforms.

astro-ph.IM↗

arXiv2022

Fixed Depth Hamiltonian Simulation via Cartan Decomposition

Simulating quantum dynamics on classical computers is challenging for large systems due to the significant memory requirements. Simulation on quantum computers is a promising alternative, but fully optimizing quantum circuits to minimize limited quantum resources remains an open problem. We tackle this problem presenting a constructive algorithm, based on Cartan decomposition of the Lie algebra generated by the Hamiltonian, that generates quantum circuits with time-independent depth. We highlight our algorithm for special classes of models, including Anderson localization in one dimensional transverse field XY model, where a O(n^2)-gate circuits naturally emerge. Compared to product formulas with significantly larger gate counts, our algorithm drastically improves simulation precision. In addition to providing exact circuits for a broad set of spin and fermionic models, our algorithm provides broad analytic and numerical insight into optimal Hamiltonian simulations.

quant-ph↗

arXiv2022

Edge-enhanced Feature Distillation Network for Efficient Super-Resolution

With the recently massive development in convolution neural networks, numerous lightweight CNN-based image super-resolution methods have been proposed for practical deployments on edge devices. However, most existing methods focus on one specific aspect: network or loss design, which leads to the difficulty of minimizing the model size. To address the issue, we conclude block devising, architecture searching, and loss design to obtain a more efficient SR structure. In this paper, we proposed an edge-enhanced feature distillation network, named EFDN, to preserve the high-frequency information under constrained resources. In detail, we build an edge-enhanced convolution block based on the existing reparameterization methods. Meanwhile, we propose edge-enhanced gradient loss to calibrate the reparameterized path training. Experimental results show that our edge-enhanced strategies preserve the edge and significantly improve the final restoration quality. Code is available at https://github.com/icandle/EFDN.

cs.CV↗

arXiv2022

Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information

Image transformation, a class of vision and graphics problems whose goal is to learn the mapping between an input image and an output image, develops rapidly in the context of deep neural networks. In Computer Vision (CV), many problems can be regarded as the image transformation task, e.g., semantic segmentation and style transfer. These works have different topics and motivations, making the image transformation task flourishing. Some surveys only review the research on style transfer or image-to-image translation, all of which are just a branch of image transformation. However, none of the surveys summarize those works together in a unified framework to our best knowledge. This paper proposes a novel learning framework including Independent learning, Guided learning, and Cooperative learning, called the IGC learning framework. The image transformation we discuss mainly involves the general image-to-image translation and style transfer about deep neural networks. From the perspective of this framework, we review those subtasks and give a unified interpretation of various scenarios. We categorize related subtasks about the image transformation according to similar development trends. Furthermore, experiments have been performed to verify the effectiveness of IGC learning. Finally, new research directions and open problems are discussed for future research.

cs.CV↗

arXiv2022

Automatic Prosody Annotation with Pre-Trained Text-Speech Model

Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability. However, the acquisition of prosodic boundary labels relies on manual annotation, which is costly and time-consuming. In this paper, we propose to automatically extract prosodic boundary labels from text-audio data via a neural text-speech model with pre-trained audio encoders. This model is pre-trained on text and speech data separately and jointly fine-tuned on TTS data in a triplet format: {speech, text, prosody}. The experimental results on both automatic evaluation and human evaluation demonstrate that: 1) the proposed text-speech prosody annotation framework significantly outperforms text-only baselines; 2) the quality of automatic prosodic boundary annotations is comparable to human annotations; 3) TTS systems trained with model-annotated boundaries are slightly better than systems that use manual ones.

cs.SD↗

arXiv2022

Language Models Can See: Plugging Visual Controls in Text Generation

Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process could be guided by modalities beyond text such as images. In this work, we propose a training-free framework, called MAGIC (iMAge-Guided text generatIon with CLIP), for plugging in visual controls in the generation process and enabling LMs to perform multimodal tasks (e.g., image captioning) in a zero-shot manner. MAGIC is a simple yet efficient plug-and-play framework, which directly combines an off-the-shelf LM (i.e., GPT-2) and an image-text matching model (i.e., CLIP) for image-grounded text generation. During decoding, MAGIC influences the generation of the LM by introducing a CLIP-induced score, called magic score, which regularizes the generated result to be semantically related to a given image while being coherent to the previously generated context. Notably, the proposed decoding scheme does not involve any gradient update operation, therefore being computationally efficient. On the challenging task of zero-shot image captioning, MAGIC outperforms the state-of-the-art method by notable margins with a nearly 27 times decoding speedup. MAGIC is a flexible framework and is theoretically compatible with any text generation tasks that incorporate image grounding. In the experiments, we showcase that it is also capable of performing visually grounded story generation given both an image and a text prompt.

cs.CV↗

arXiv2022

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring, color drifting and texture missing. Moreover, those varied artifacts make image quality metrics correlate badly with human perceptual quality. In this paper, we propose PO-ELIC, i.e., Perception-Oriented Efficient Learned Image Coding. To be specific, we adapt ELIC, one of the state-of-the-art LIC models, with adversarial training techniques. We apply a mixture of losses including hinge-form adversarial loss, Charbonnier loss, and style loss, to finetune the model towards better perceptual quality. Experimental results demonstrate that our method achieves comparable perceptual quality with HiFiC with much lower bitrate.

eess.IV↗

arXiv2022

Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities

In recent years, sequential recommender systems (SRSs) and session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs to capture users' short-term but dynamic preferences for enabling more timely and accurate recommendations. Although SRSs and SBRSs have been extensively studied, there are many inconsistencies in this area caused by the diverse descriptions, settings, assumptions and application domains. There is no work to provide a unified framework and problem statement to remove the commonly existing and various inconsistencies in the area of SR/SBR. There is a lack of work to provide a comprehensive and systematic demonstration of the data characteristics, key challenges, most representative and state-of-the-art approaches, typical real-world applications and important future research directions in the area. This work aims to fill in these gaps so as to facilitate further research in this exciting and vibrant area.

cs.IR↗

arXiv2022

Journey of Migrating Millions of Queries on The Cloud

Treasure Data is processing millions of distributed SQL queries every day on the cloud. Upgrading the query engine service at this scale is challenging because we need to migrate all of the production queries of the customers to a new version while preserving the correctness and performance of the data processing pipelines. To ensure the quality of the query engines, we utilize our query logs to build customer-specific benchmarks and replay these queries with real customer data in a secure pre-production environment. To simulate millions of queries, we need effective minimization of test query sets and better reporting of the simulation results to proactively find incompatible changes and performance regression of the new version. This paper describes the overall design of our system and shares various challenges in maintaining the quality of the query engine service on the cloud.

cs.DB↗

arXiv2022

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

cs.CV↗

arXiv2022

Effectively Using Long and Short Sessions for Multi-Session-based Recommendations

It is not accurate to make recommendations only based one single current session. Therefore, multi-session-based recommendation(MSBR) is a solution for the problem. Compared with the previous MSBR models, we have made three improvements in this paper. First, the previous work choose to use all the history sessions of the user and/or of his similar users. When the user's current interest changes greatly from the past, most of these sessions can only have negative impacts. Therefore, we select a large number of randomly chosen sessions from the dataset as candidate sessions to avoid over depending on history data. Then we only choose to use the most similar sessions to get the most useful information while reduce the noise caused by dissimilar sessions. Second, in real-world datasets, short sessions account for a large proportion. The RNN often used in previous work is not suitable to process short sessions, because RNN only focuses on the sequential relationship, which we find is not the only relationship between items in short sessions. So, we designed a more suitable method named GAFE based on attention to process short sessions. Third, Although there are few long sessions, they can not be ignored. Not like previous models, which simply process long sessions in the same way as short sessions, we propose LSIS, which can split the interest of long sessions, to make better use of long sessions. Finally, to help recommendations, we also have considered users' long-term interests captured by a multi-layer GRU. Considering the four points above, we built the model ENIREC. Experiments on two real-world datasets show that the comprehensive performance of ENIREC is better than other existing models.

cs.IR↗

arXiv2022

Exploring Dense Retrieval for Dialogue Response Selection

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and response candidates. While remarkably effective, these models also bring in a steep increase in computational cost. Consequently, such models can only be used as a re-rank module in practice. In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model. To push the limits of dense retrieval, we design an interaction layer upon the dense retrieval models and apply a set of tailor-designed learning strategies. Our model shows superiority over strong baselines on the conventional re-rank evaluation setting, which is remarkable given its efficiency. To verify the effectiveness of our approach in realistic scenarios, we also conduct full-rank evaluation, where the target is to select proper responses from a full candidate pool that may contain millions of candidates and evaluate them fairly through human annotations. Our proposed model notably outperforms pipeline baselines that integrate fast recall and expressive re-rank modules. Human evaluation results show that enlarging the candidate pool with nonparallel corpora improves response quality further.

cs.CL↗

arXiv2022

Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks

Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost. However, compressing Transformer remains as an open problem due to its internal complexity of the layer designs, i.e., Multi-Head Attention (MHA) and Feed-Forward Network (FFN). To address this issue, we introduce Group-wise Transformation towards a universal yet lightweight Transformer for vision-and-language tasks, termed as LW-Transformer. LW-Transformer applies Group-wise Transformation to reduce both the parameters and computations of Transformer, while also preserving its two main properties, i.e., the efficient attention modeling on diverse subspaces of MHA, and the expanding-scaling feature transformation of FFN. We apply LW-Transformer to a set of Transformer-based networks, and quantitatively measure them on three vision-and-language tasks and six benchmark datasets. Experimental results show that while saving a large number of parameters and computations, LW-Transformer achieves very competitive performance against the original Transformer networks for vision-and-language tasks. To examine the generalization ability, we also apply our optimization strategy to a recently proposed image Transformer called Swin-Transformer for image classification, where the effectiveness can be also confirmed

cs.CV↗

arXiv2022

Prospects and Strategies for Detecting Nonlinear Gravitational Wave Burst with Memory from Potential Merger Event SDSSJ1430$+$2303 by Pulsar Timing Arrays

The recently observed chirping signature in the light curves of Seyfert 1 galaxy SDSSJ1430$+$2303 could be explained by a late-inspiralling supermassive binary black hole (SMBBH) system in the galactic center, which will merge in the near future (or could have merged already). For the merging SMBBH scenario, SDSSJ1430$+$2303 can be a source of nonlinear gravitational wave (GW) burst with memory (BWM), which may provide a promising target for future pulsar timing array (PTA) observations. In this work, we investigate the prospects for detecting the BWM signal from SDSSJ1430$+$2303 by the International PTA (IPTA) and FAST-PTA in the next $5$ years. We firstly propose strategies on searching for this target signal, including the selection of millisecond pulsars (MSPs) and the distribution of observation time. Then we simulate PTA observations based on the proposed strategies and obtain the probability density functions of the network signal-to-noise ratio and parameter-estimation errors of the BWM signal, considering the uncertainties of parameters of the SMBBH and both white and red noises of the selected MSPs. Our result shows that although IPTA can marginally detect the BWM in $5$ years, FAST-PTA can detect it with significantly higher confidence. Moreover, the archived IPTA data is important in estimating the merger time of the SMBBH, when combined with the FAST-PTA data. This work can serve as a guidance for future PTA observations and multi-messenger studies on SDSSJ1430$+$2303 and similar systems.

astro-ph.HE↗

arXiv2022

Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain

JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems. However, most recent progress on image compression mainly focuses on uncompressed images while ignoring trillions of already-existing JPEG images. To compress these JPEG images adequately and restore them back to JPEG format losslessly when needed, we propose a deep learning based JPEG recompression method that operates on DCT domain and propose a Multi-Level Cross-Channel Entropy Model to compress the most informative Y component. Experiments show that our method achieves state-of-the-art performance compared with traditional JPEG recompression methods including Lepton, JPEG XL and CMIX. To the best of our knowledge, this is the first learned compression method that losslessly transcodes JPEG images to more storage-saving bitstreams.

eess.IV↗

arXiv2022

Demonstrating shareability of multipartite Einstein-Podolsky-Rosen steering

Einstein-Podolsky-Rosen (EPR) steering, a category of quantum nonlocal correlations describing the ability of one observer to influence another party's state via local measurements, is different from both entanglement and Bell nonlocality by possessing an asymmetric property. For multipartite EPR steering, the monogamous situation, where two observers cannot simultaneously steer the state of the third party, has been investigated rigorously both in theory and experiment. In contrast to the monogamous situation, the shareability of EPR steering in reduced subsystems allows the state of one party to be steered by two or more observers and thus reveals more configurations of multipartite EPR steering. However, the experimental implementation of such a kind of shareability has still been absent until now. Here, in an optical experiment, we provide a proof-of-principle demonstration of the shareability of EPR steering without the constraint of monogamy in a three-qubit system. Moreover, based on the reduced bipartite EPR steering detection results, we verify the genuine three-qubit entanglement results. This work provides a complementary viewpoint for understanding multipartite EPR steering and has potential applications in many quantum information protocols, such as multipartite entanglement detection, quantum cryptography, and the construction of quantum networks.

quant-ph↗

arXiv2022

ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough investigation of the architecture design of learned image compression, regarding both compression performance and running speed, is essential. In this paper, we first propose uneven channel-conditional adaptive coding, motivated by the observation of energy compaction in learned image compression. Combining the proposed uneven grouping model with existing context models, we obtain a spatial-channel contextual adaptive model to improve the coding performance without damage to running speed. Then we study the structure of the main transform and propose an efficient model, ELIC, to achieve state-of-the-art speed and compression ability. With superior performance, the proposed model also supports extremely fast preview decoding and progressive decoding, which makes the coming application of learning-based image compression more promising.

cs.CV↗

arXiv2022

Floquet topological properties in the Non-Hermitian long-range system with complex hopping amplitudes

Non-equilibrium phases of matter have attracted much attention in recent years, among which the Floquet phase is a hot point. In this work, based on the Periodic driving Non-Hermitian model, we reveal that the winding number calculated in the framework of the Bloch band theory has a direct connection with the number of edge states even the Non-Hermiticity is present. Further, we find that the change of the phase of the hopping amplitude can induce the topological phase transitions. Precisely speaking, the increase of the value of the phase can bring the system into the larger topological phase. Moreover, it can be unveiled that the introduction of the purely imaginary hopping term brings an extremely rich phase diagram. In addition, we can select the even topological invariant exactly from the unlimited winding numbers if we only consider the next-nearest neighbor hopping term. Here, the results obtained may be useful for understanding the Periodic driving Non-Hermitian theory.

quant-ph↗