Searcharxiv⌕ Search

arXiv subjects

Yi Lin

Publications and source records attributed to Yi Lin.

At least 127 records · Page 7Linked to original sources
arXiv2021

Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network

Automated methods for detecting pulmonary embolisms (PEs) on CT pulmonary angiography (CTPA) images are of high demand. Existing methods typically employ separate steps for PE candidate detection and false positive removal, without considering the ability of the other step. As a result, most existing methods usually suffer from a high false positive rate in order to achieve an acceptable sensitivity. This study presents an end-to-end trainable convolutional neural network (CNN) where the two steps are optimized jointly. The proposed CNN consists of three concatenated subnets: 1) a novel 3D candidate proposal network for detecting cubes containing suspected PEs, 2) a 3D spatial transformation subnet for generating fixed-sized vessel-aligned image representation for candidates, and 3) a 2D classification network which takes the three cross-sections of the transformed cubes as input and eliminates false positives. We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78.9%, 80.7% and 80.7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods. We have further evaluated our system on our own dataset consisting of 129 CTPA data with a total of 269 emboli. Our system achieves a sensitivity of 63.2%, 78.9% and 86.8% at 2 false positives per volume at 0mm, 2mm and 5mm localization error.

cs.CV↗
arXiv2021

Speech recognition for air traffic control via feature learning and end-to-end training

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss to build an end-to-end ASR model. Facing the complex environments of ATC speech, instead of the handcrafted features, a learning block is designed to extract informative features from raw waveforms for acoustic modeling. Both the SincNet and 1D convolution blocks are applied to process the raw waveforms, whose outputs are concatenated to the RNN layers for the temporal modeling. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner, i.e., from waveform to text. Finally, the multilingual issue in the ATC domain is also considered to achieve the ASR task by constructing a combined vocabulary of Chinese characters and English letters. The proposed approach is validated on a multilingual real-world corpus (ATCSpeech), and the experimental results demonstrate that the proposed approach outperforms other baselines, achieving a 6.9\% character error rate.

cs.SD↗
arXiv2021

Dual-microcomb generation in a synchronously-driven waveguide ring resonator

Microcombs -- optical frequency combs generated in coherently-driven nonlinear microresonators -- have attracted significant attention over the last decade. The ability to generate two such combs in a single resonator device has in particular enabled a host of applications from spectroscopy to imaging. Concurrently, novel comb generation techniques such as synchronous pulsed driving have been developed to enhance the efficiency and flexibility of microcomb generation. Here we report on the first experimental demonstration of dual-microcomb generation via synchronous pulsed pumping of a single microresonator. Specifically, we use two electro-optically generated pulse trains derived from a common continuous wave laser to simultaneously drive two orthogonal polarization modes of an integrated silica ring resonator, observing the generation of coherent dissipative Kerr cavity soliton combs on both polarization axes. Thanks to the resonator birefringence, the two soliton combs are associated with different repetition rates, thus realizing a dual-microcomb source. To illustrate the source's application potential, we demonstrate proof-of-concept spectroscopic measurements.

physics.optics↗
arXiv2021

Fast-Racing: An Open-source Strong Baseline for SE(3) Planning in Autonomous Drone Racing

With the autonomy of aerial robots advances in recent years, autonomous drone racing has drawn increasing attention. In a professional pilot competition, a skilled operator always controls the drone to agilely avoid obstacles in aggressive attitudes, for reaching the destination as fast as possible. Autonomous flight like elite pilots requires planning in SE(3), whose non-triviality and complexity hindering a convincing solution in our community by now. To bridge this gap, this paper proposes an open-source baseline, which includes a high-performance SE(3) planner and a challenging simulation platform tailored for drone racing. We specify the SE(3) trajectory generation as a soft-penalty optimization problem, and speed up the solving process utilizing its underlying parallel structure. Moreover, to provide a testbed for challenging the planner, we develop delicate drone racing tracks which mimic real-world set-up and necessities planning in SE(3). Besides, we provide necessary system components such as common map interfaces and a baseline controller, to make our work plug-in-and-use. With our baseline, we hope to future foster the research of SE(3) planning and the competition of autonomous drone racing.

cs.RO↗
arXiv2021

A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks

Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making. Luckily, medical AEs are also easy to detect in hierarchical feature space per our study herein. To better understand this phenomenon, we thoroughly investigate the intrinsic characteristic of medical AEs in feature space, providing both empirical evidence and theoretical explanations for the question: why are medical adversarial attacks easy to detect? We first perform a stress test to reveal the vulnerability of deep representations of medical images, in contrast to natural images. We then theoretically prove that typical adversarial attacks to binary disease diagnosis network manipulate the prediction by continuously optimizing the vulnerable representations in a fixed direction, resulting in outlier features that make medical AEs easy to detect. However, this vulnerability can also be exploited to hide the AEs in the feature space. We propose a novel hierarchical feature constraint (HFC) as an add-on to existing adversarial attacks, which encourages the hiding of the adversarial representation within the normal feature distribution. We evaluate the proposed method on two public medical image datasets, namely {Fundoscopy} and {Chest X-Ray}. Experimental results demonstrate the superiority of our adversarial attack method as it bypasses an array of state-of-the-art adversarial detectors more easily than competing attack methods, supporting that the great vulnerability of medical features allows an attacker more room to manipulate the adversarial representations.

cs.CV↗
arXiv2021

ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems

In this paper, a multilingual end-to-end framework, called as ATCSpeechNet, is proposed to tackle the issue of translating communication speech into human-readable text in air traffic control (ATC) systems. In the proposed framework, we focus on integrating the multilingual automatic speech recognition (ASR) into one model, in which an end-to-end paradigm is developed to convert speech waveform into text directly, without any feature engineering or lexicon. In order to make up for the deficiency of the handcrafted feature engineering caused by ATC challenges, a speech representation learning (SRL) network is proposed to capture robust and discriminative speech representations from the raw wave. The self-supervised training strategy is adopted to optimize the SRL network from unlabeled data, and further to predict the speech features, i.e., wave-to-feature. An end-to-end architecture is improved to complete the ASR task, in which a grapheme-based modeling unit is applied to address the multilingual ASR issue. Facing the problem of small transcribed samples in the ATC domain, an unsupervised approach with mask prediction is applied to pre-train the backbone network of the ASR model on unlabeled data by a feature-to-feature process. Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i.e., wave-to-text. Experimental results on the ATCSpeech corpus demonstrate that the proposed approach achieves a high performance with a very small labeled corpus and less resource consumption, only 4.20% label error rate on the 58-hour transcribed corpus. Compared to the baseline model, the proposed approach obtains over 100% relative performance improvement which can be further enhanced with the increasing of the size of the transcribed samples.

cs.CL↗
arXiv2021

Improving speech recognition models with small samples for air traffic control systems

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert- and domain-dependent task. In this work, a novel training approach based on pretraining and transfer learning is proposed to address this issue, and an improved end-to-end deep learning model is developed to address the specific challenges of ASR in the ATC domain. An unsupervised pretraining strategy is first proposed to learn speech representations from unlabeled samples for a certain dataset. Specifically, a masking strategy is applied to improve the diversity of the sample without losing their general patterns. Subsequently, transfer learning is applied to fine-tune a pretrained or other optimized baseline models to finally achieves the supervised ASR task. By virtue of the common terminology used in the ATC domain, the transfer learning task can be regarded as a sub-domain adaption task, in which the transferred model is optimized using a joint corpus consisting of baseline samples and new transcribed samples from the target dataset. This joint corpus construction strategy enriches the size and diversity of the training samples, which is important for addressing the issue of the small transcribed corpus. In addition, speed perturbation is applied to augment the new transcribed samples to further improve the quality of the speech corpus. Three real ATC datasets are used to validate the proposed ASR model and training strategies. The experimental results demonstrate that the ASR performance is significantly improved on all three datasets, with an absolute character error rate only one-third of that achieved through the supervised training. The applicability of the proposed strategies to other ASR approaches is also validated.

cs.SD↗
arXiv2020

Momentum resolved ground/excited states and the ultra-fast excited state dynamics of monolayer MoS2

The emergence of transition metal dichalcogenides (TMD) as crystalline atomically thin semiconductors has created a tremendous amount of scientific and technological interest. Many novel device concepts have been proposed and realized (1-3). Nonetheless, progress in k-space investigations of ground/excited state electronic structures has been slow due to the challenge to create large scale, laterally homogeneous samples. Taking advantage of recent advancements in chemical vapor deposition, here we create a wafer-size MoS2 monolayer with well-aligned lateral orientation for advanced electron spectroscopy studies (4-6). Low energy electron diffraction and scanning tunneling microscopy (STM) demonstrate atomically clean surfaces with in-plane crystalline orientation. The ground state and excited state electronic structures are probed using scanning tunneling spectroscopy (STS), angle-resolved photoemission (ARPES) and time-resolved (tr-)ARPES. In addition to mapping out the momentum-space quasiparticle band structure in the valence and conduction bands, we unveil ultrafast excited state dynamics, including inter- and intra-valley carrier scattering and a rapid downward energy shift by ~ 0.2eV lower than the initial free carrier state at Sigma point.

cond-mat.mes-hall↗
arXiv2020

Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes

Background and Objective: Biometric measurements of fetal head are important indicators for maternal and fetal health monitoring during pregnancy. 3D ultrasound (US) has unique advantages over 2D scan in covering the whole fetal head and may promote the diagnoses. However, automatically segmenting the whole fetal head in US volumes still pends as an emerging and unsolved problem. The challenges that automated solutions need to tackle include the poor image quality, boundary ambiguity, long-span occlusion, and the appearance variability across different fetal poses and gestational ages. In this paper, we propose the first fully-automated solution to segment the whole fetal head in US volumes. Methods: The segmentation task is firstly formulated as an end-to-end volumetric mapping under an encoder-decoder deep architecture. We then combine the segmentor with a proposed hybrid attention scheme (HAS) to select discriminative features and suppress the non-informative volumetric features in a composite and hierarchical way. With little computation overhead, HAS proves to be effective in addressing boundary ambiguity and deficiency. To enhance the spatial consistency in segmentation, we further organize multiple segmentors in a cascaded fashion to refine the results by revisiting context in the prediction of predecessors. Results: Validated on a large dataset collected from 100 healthy volunteers, our method presents superior segmentation performance (DSC (Dice Similarity Coefficient), 96.05%), remarkable agreements with experts. With another 156 volumes collected from 52 volunteers, we ahieve high reproducibilities (mean standard deviation 11.524 mL) against scan variations. Conclusion: This is the first investigation about whole fetal head segmentation in 3D US. Our method is promising to be a feasible solution in assisting the volumetric US-based prenatal studies.

eess.IV↗
arXiv2020

Harmonic and rational harmonic driving of microresonator soliton frequency combs

With demonstrated applications ranging from metrology to telecommunications, soliton microresonator frequency combs have emerged over the past decade as a remarkable new technology. However, standard implementations only allow for the generation of combs whose repetition rate is tied close to the fundamental resonator free-spectral range (FSR), offering little or no dynamic control over the comb line spacing. Here we propose and experimentally demonstrate harmonic and rational harmonic driving as novel techniques that allow for the robust generation of soliton frequency combs with discretely adjustable frequency spacing. By driving an integrated Kerr microresonator with a periodic train of picosecond pulses whose repetition rate is set close to an integer harmonic of the 3.23 GHz cavity FSR, we deterministically generate soliton frequency combs with frequency spacings discretely adjustable between 3.23 GHz and 19.38 GHz. More remarkably, we also demonstrate that driving the resonator at rational fractions of the FSR allows for the generation of combs whose frequency spacing corresponds to an integer harmonic of the pump repetition rate. By measuring the combs' radio-frequency spectrum, we confirm operation in the low-noise soliton regime with no supermode noise. The novel techniques demonstrated in our work provide new degrees of freedom for the design of synchronously pumped soliton frequency combs.

physics.optics↗
arXiv2019

ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment

Automatic Speech Recognition (ASR) is greatly developed in recent years, which expedites many applications on other fields. For the ASR research, speech corpus is always an essential foundation, especially for the vertical industry, such as Air Traffic Control (ATC). There are some speech corpora for common applications, public or paid. However, for the ATC, it is difficult to collect raw speeches from real systems due to safety issues. More importantly, for a supervised learning task like ASR, annotating the transcription is a more laborious work, which hugely restricts the prospect of ASR application. In this paper, a multilingual speech corpus (ATCSpeech) from real ATC systems, including accented Mandarin Chinese and English, is built and released to encourage the non-commercial ASR research in ATC domain. The corpus is detailly introduced from the perspective of data amount, speaker gender and role, speech quality and other attributions. In addition, the performance of our baseline ASR models is also reported. A community edition for our speech database can be applied and used under a special contrast. To our best knowledge, this is the first work that aims at building a real and multilingual ASR corpus for the air traffic related research.

cs.CL↗
arXiv2019

Real-Time Machine Learning Based Fiber-Induced Nonlinearity Compensation in Energy-Efficient Coherent Optical Networks

We experimentally demonstrate the first field-programmable gate-array-based real-time fiber nonlinearity compensator (NLC) using sparse K-means++ machine learning clustering in an energy-efficient 40-Gb/s 16-quadrature amplitude modulated self-coherent optical system. Our real-time NLC shows up to 3 dB improvement in Q-factor compared to linear equalization at 50 km of transmission.

physics.app-ph↗
arXiv2019

STELA: A Real-Time Scene Text Detector with Learned Anchor

To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks. In this work, we present a simple and intuitive method for multi-oriented text detection where each location of feature maps only associates with one reference box. The idea is inspired from the twostage R-CNN framework that can estimate the location of objects with any shape by using learned proposals. The aim of our method is to integrate this mechanism into a onestage detector and employ the learned anchor which is obtained through a regression operation to replace the original one into the final predictions. Based on RetinaNet, our method achieves competitive performances on several public benchmarks with a totally real-time efficiency (26:5fps at 800p), which surpasses all of anchor-based scene text detectors. In addition, with less attention on anchor design, we believe our method is easy to be applied on other analogous detection tasks. The code will publicly available at https://github.com/xhzdeng/stela.

cs.CV↗
arXiv2019

Matrix embedding method in match for session-based recommendation

Session based model is widely used in recommend system. It use the user click sequence as input of a Recurrent Neural Network (RNN), and get the output of the RNN network as the vector embedding of the session, and use the inner product of the vector embedding of session and the vector embedding of the next item as the score that is the metric of the interest to the next item. This method can be used for the "match" stage for the recommendation system whose item number is very big by using some index method like KD-Tree or Ball-Tree and etc.. But this method repudiate the variousness of the interest of user in a session. We generated the model to modify the vector embedding of session to a symmetric matrix embedding, that is equivalent to a quadratic form on the vector space of items. The score is builded as the value of the vector embedding of next item under the quadratic form. The eigenvectors of the symmetric matrix embedding corresponding to the positive eigenvalues are conjectured to represent the interests of user in the session. This method can be used for the "match" stage also. The experiments show that this method is better than the method of vector embedding.

cs.LG↗
arXiv2019

Detecting Multi-Oriented Text with Corner-based Region Proposals

Previous approaches for scene text detection usually rely on manually defined sliding windows. This work presents an intuitive two-stage region-based method to detect multi-oriented text without any prior knowledge regarding the textual shape. In the first stage, we estimate the possible locations of text instances by detecting and linking corners instead of shifting a set of default anchors. The quadrilateral proposals are geometry adaptive, which allows our method to cope with various text aspect ratios and orientations. In the second stage, we design a new pooling layer named Dual-RoI Pooling which embeds data augmentation inside the region-wise subnetwork for more robust classification and regression over these proposals. Experimental results on public benchmarks confirm that the proposed method is capable of achieving comparable performance with state-of-the-art methods. The code is publicly available at https://github.com/xhzdeng/crpn

cs.CV↗