arXiv subjects

Ruili Wang

Publications and source records attributed to Ruili Wang.

25 records · Page 2Linked to original sources

arXiv2021

DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals

We propose a novel pitch estimation technique called DeepF0, which leverages the available annotated data to directly learns from the raw audio in a data-driven manner. F0 estimation is important in various speech processing and music information retrieval applications. Existing deep learning models for pitch estimations have relatively limited learning capabilities due to their shallow receptive field. The proposed model addresses this issue by extending the receptive field of a network by introducing the dilated convolutional blocks into the network. The dilation factor increases the network receptive field exponentially without increasing the parameters of the model exponentially. To make the training process more efficient and faster, DeepF0 is augmented with residual blocks with residual connections. Our empirical evaluation demonstrates that the proposed model outperforms the baselines in terms of raw pitch accuracy and raw chroma accuracy even using 77.4% fewer network parameters. We also show that our model can capture reasonably well pitch estimation even under the various levels of accompaniment noise.

eess.AS↗

arXiv2020

Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies

Generative Adversarial Networks (GANs) have been extremely successful in various application domains such as computer vision, medicine, and natural language processing. Moreover, transforming an object or person to a desired shape become a well-studied research in the GANs. GANs are powerful models for learning complex distributions to synthesize semantically meaningful samples. However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training. Given the current fast GANs development, in this survey, we provide a comprehensive review of adversarial models for image synthesis. We summarize the synthetic image generation methods, and discuss the categories including image-to-image translation, fusion image generation, label-to-image mapping, and text-to-image translation. We organize the literature based on their base models, developed ideas related to architectures, constraints, loss functions, evaluation metrics, and training datasets. We present milestones of adversarial models, review an extensive selection of previous works in various categories, and present insights on the development route from the model-based to data-driven methods. Further, we highlight a range of potential future research directions. One of the unique features of this review is that all software implementations of these GAN methods and datasets have been collected and made available in one place at https://github.com/pshams55/GAN-Case-Study.

cs.CV↗

arXiv2020

Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks

Road extraction in remote sensing images is of great importance for a wide range of applications. Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears correct and complete. Moreover, they suffer from either insufficient training data or high costs of manual annotation. To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation. We incorporate a feature pyramid network into generative adversarial networks to minimize the difference between the source and target domains. A generator is learned to produce quality synthetic images, and the discriminator attempts to distinguish them. We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales objects. Indeed, a novel scale-wise architecture is introduced to learn from the multi-level feature maps and improve the semantics of the features. For optimization, the model is trained by a joint reconstruction loss function, which minimizes the difference between the fake images and the real ones. A wide range of experiments on three datasets prove the superior performance of the proposed approach in terms of accuracy and efficiency. In particular, our model achieves state-of-the-art 78.86 IOU on the Massachusetts dataset with 14.89M parameters and 86.78B FLOPs, with 4x fewer FLOPs but higher accuracy (+3.47% IOU) than the top performer among state-of-the-art approaches used in the evaluation.

cs.CV↗

arXiv2020

A novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images

Sea-land segmentation is an important process for many key applications in remote sensing. Proper operative sea-land segmentation for remote sensing images remains a challenging issue due to complex and diverse transition between sea and lands. Although several Convolutional Neural Networks (CNNs) have been developed for sea-land segmentation, the performance of these CNNs is far from the expected target. This paper presents a novel deep neural network structure for pixel-wise sea-land segmentation, a Residual Dense U-Net (RDU-Net), in complex and high-density remote sensing images. RDU-Net is a combination of both down-sampling and up-sampling paths to achieve satisfactory results. In each down- and up-sampling path, in addition to the convolution layers, several densely connected residual network blocks are proposed to systematically aggregate multi-scale contextual information. Each dense network block contains multilevel convolution layers, short-range connections and an identity mapping connection which facilitates features re-use in the network and makes full use of the hierarchical features from the original images. These proposed blocks have a certain number of connections that are designed with shorter distance backpropagation between the layers and can significantly improve segmentation results whilst minimizing computational costs. We have performed extensive experiments on two real datasets Google Earth and ISPRS and compare the proposed RDUNet against several variations of Dense Networks. The experimental results show that RDUNet outperforms the other state-of-the-art approaches on the sea-land segmentation tasks.

eess.IV↗

arXiv2018

KDSL: a Knowledge-Driven Supervised Learning Framework for Word Sense Disambiguation

We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning. First, from WordNet, we automatically construct a semantic knowledge base called DisDict, which provides refined feature words that highlight the differences among word senses, i.e., synsets. Second, we automatically generate new sense-labeled data by DisDict from unlabeled corpora. Third, these generated data, together with manually labeled data and unlabeled data, are fed to a neural framework conducting supervised and unsupervised learning jointly to model the semantic relations among synsets, feature words and their contexts. The experimental results show that KDSL outperforms several representative state-of-the-art methods on various major benchmarks. Interestingly, it performs relatively well even when manually labeled data is unavailable, thus provides a potential solution for similar tasks in a lack of manual annotations.

cs.CL↗

arXiv2008

Theoretical investigation of synchronous totally asymmetric exclusion processes on lattices with multiple-input-single-output junctions

In this paper, we investigate the dynamics of synchronous totally asymmetric exclusion processes on lattices with a multiple-input single-output (MISO) junction, which consists of m subchains for the input and one main chain for the output. A MISO junction is a type of complex geometry that is relevant to many biological processes as well as vehicular and pedestrian traffic flow. A mean-field approach is developed to deal with the junction that connects the subchains and the main chain. Theoretical results for stationary particle currents, density profiles, and a phase diagram have been obtained. It is found that the phase boundary moves toward the left in the phase diagram with an increase of the number of subchains. The nonequilibrium stationary states, stationary-state phases, and phase boundaries are determined by the boundary conditions of the system as well as by the number of subchains. The density profiles obtained from computer simulations show very good agreement with our theoretical analysis.

physics.bio-ph↗

arXiv2007

Effects of Langmuir Kinetics of Two-Lane Totally Asymmetric Exclusion Processes in Protein Traffic

In this paper, we study a two-lane totally asymmetric simple exclusion process (TASEP) coupled with random attachment and detachment of particles (Langmuir kinetics) in both lanes under open boundary conditions. Our model can describe the directed motion of molecular motors, attachment and detachment of motors, and free inter-lane transition of motors between filaments. In this paper, we focus on some finite-size effects of the system because normally the sizes of most real systems are finite and small (e.g., size $\leq 10,000$). A special finite-size effect of the two-lane system has been observed, which is that the density wall moves left first and then move towards the right with the increase of the lane-changing rate. We called it the jumping effect. We find that increasing attachment and detachment rates will weaken the jumping effect. We also confirmed that when the size of the two-lane system is large enough, the jumping effect disappears, and the two-lane system has a similar density profile to a single-lane TASEP coupled with Langmuir kinetics. Increasing lane-changing rates has little effect on density and current after the density reaches maximum. Also, lane-changing rate has no effect on density profiles of a two-lane TASEP coupled with Langmuir kinetics at a large attachment/detachment rate and/or a large system size. Mean-field approximation is presented and it agrees with our Monte Carlo simulations.

q-bio.QM↗