arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 469 records · Page 26Linked to original sources

arXiv2021

A Hierarchical Conditional Random Field-based Attention Mechanism Approach for Gastric Histopathology Image Classification

In the Gastric Histopathology Image Classification (GHIC) tasks, which are usually weakly supervised learning missions, there is inevitably redundant information in the images. Therefore, designing networks that can focus on effective distinguishing features has become a popular research topic. In this paper, to accomplish the tasks of GHIC superiorly and to assist pathologists in clinical diagnosis, an intelligent Hierarchical Conditional Random Field based Attention Mechanism (HCRF-AM) model is proposed. The HCRF-AM model consists of an Attention Mechanism (AM) module and an Image Classification (IC) module. In the AM module, an HCRF model is built to extract attention regions. In the IC module, a Convolutional Neural Network (CNN) model is trained with the attention regions selected and then an algorithm called Classification Probability-based Ensemble Learning is applied to obtain the image-level results from patch-level output of the CNN. In the experiment, a classification specificity of 96.67% is achieved on a gastric histopathology dataset with 700 images. Our HCRF-AM model demonstrates high classification performance and shows its effectiveness and future potential in the GHIC field.

cs.CV↗

arXiv2021

From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation

Animal pose estimation is an important field that has received increasing attention in the recent years. The main challenge for this task is the lack of labeled data. Existing works circumvent this problem with pseudo labels generated from data of other easily accessible domains such as synthetic data. However, these pseudo labels are noisy even with consistency check or confidence-based filtering due to the domain shift in the data. To solve this problem, we design a multi-scale domain adaptation module (MDAM) to reduce the domain gap between the synthetic and real data. We further introduce an online coarse-to-fine pseudo label updating strategy. Specifically, we propose a self-distillation module in an inner coarse-update loop and a mean-teacher in an outer fine-update loop to generate new pseudo labels that gradually replace the old ones. Consequently, our model is able to learn from the old pseudo labels at the early stage, and gradually switch to the new pseudo labels to prevent overfitting in the later stage. We evaluate our approach on the TigDog and VisDA 2019 datasets, where we outperform existing approaches by a large margin. We also demonstrate the generalization ability of our model by testing extensively on both unseen domains and unseen animal categories. Our code is available at the project website.

cs.CV↗

arXiv2021

A SARS-CoV-2 Microscopic Image Dataset with Ground Truth Images and Visual Features

SARS-CoV-2 has characteristics of wide contagion and quick propagation velocity. To analyse the visual information of it, we build a SARS-CoV-2 Microscopic Image Dataset (SC2-MID) with 48 electron microscopic images and also prepare their ground truth images. Furthermore, we extract multiple classical features and novel deep learning features to describe the visual information of SARS-CoV-2. Finally, it is proved that the visual features of the SARS-CoV-2 images which are observed under the electron microscopic can be extracted and analysed.

eess.IV↗

arXiv2021

1550 nm compatible ultrafast photoconductive material based on a GaAs/ErAs/GaAs heterostructure

The sub-bandgap absorption and ultrafast relaxation in a GaAs/ErAs/GaAs heterostructure are reported. The infrared absorption and 1550 nm-excited ultrafast photo-response are studied by Fourier transform infrared (FTIR) spectrometry and time-domain pump-probe technique. The two absorption peaks located at 2.0 um (0.62 eV) and 2.7 um (0.45 eV) are originated from the ErAs/GaAs interfacial Schottky states and sub-bandgap transition within GaAs, respectively. The photo-induced carrier lifetime, excited using 1550 nm light, is measured to be as low as 190 fs for the GaAs/ErAs/GaAs heterostructure, making it a promising material for 1550-nm-technology-compatible, high critical-breakdown-field THz devices. The relaxation mechanism is proposed and the functionality of ErAs is revealed.

cond-mat.mtrl-sci↗

arXiv2021

Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network

Hyperparameter optimization is a challenging problem in developing deep neural networks. Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN). Conventional transfer CNN models are usually manually designed based on intuition. In this paper, a genetic algorithm is applied to select trainable layers of the transfer model. The filter criterion is constructed by accuracy and the counts of the trainable layers. The results show that the method is competent in this task. The system will converge with a precision of 97% in the classification of Cats and Dogs datasets, in no more than 15 generations. Moreover, backward inference according the results of the genetic algorithm shows that our method can capture the gradient features in network layers, which plays a part on understanding of the transfer AI models.

cs.NE↗

arXiv2021

A New Pairwise Deep Learning Feature For Environmental Microorganism Image Analysis

Environmental microorganism (EM) offers a high-efficient, harmless, and low-cost solution to environmental pollution. They are used in sanitation, monitoring, and decomposition of environmental pollutants. However, this depends on the proper identification of suitable microorganisms. In order to fasten, low the cost, increase consistency and accuracy of identification, we propose the novel pairwise deep learning features to analyze microorganisms. The pairwise deep learning features technique combines the capability of handcrafted and deep learning features. In this technique we, leverage the Shi and Tomasi interest points by extracting deep learning features from patches which are centered at interest points locations. Then, to increase the number of potential features that have intermediate spatial characteristics between nearby interest points, we use Delaunay triangulation theorem and straight-line geometric theorem to pair the nearby deep learning features. The potential of pairwise features is justified on the classification of EMs using SVMs, k-NN, and Random Forest classifier. The pairwise features obtain outstanding results of 99.17%, 91.34%, 91.32%, 91.48%, and 99.56%, which are the increase of about 5.95%, 62.40%, 62.37%, 61.84%, and 3.23% in accuracy, F1-score, recall, precision, and specificity respectively, compared to non-paired deep learning features.

cs.CV↗

arXiv2021

A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches

With the development of computer-aided diagnosis (CAD) and image scanning technology, Whole-slide Image (WSI) scanners are widely used in the field of pathological diagnosis. Therefore, WSI analysis has become the key to modern digital pathology. Since 2004, WSI has been used more and more in CAD. Since machine vision methods are usually based on semi-automatic or fully automatic computers, they are highly efficient and labor-saving. The combination of WSI and CAD technologies for segmentation, classification, and detection helps histopathologists obtain more stable and quantitative analysis results, save labor costs and improve diagnosis objectivity. This paper reviews the methods of WSI analysis based on machine learning. Firstly, the development status of WSI and CAD methods are introduced. Secondly, we discuss publicly available WSI datasets and evaluation metrics for segmentation, classification, and detection tasks. Then, the latest development of machine learning in WSI segmentation, classification, and detection are reviewed continuously. Finally, the existing methods are studied, the applicabilities of the analysis methods are analyzed, and the application prospects of the analysis methods in this field are forecasted.

cs.CV↗

arXiv2021

Direct observation of layer-stacking and oriented wrinkles in multilayer hexagonal boron nitride

Hexagonal boron nitride (h-BN) has long been recognized as an ideal substrate for electronic devices due to its dangling-bond-free surface, insulating nature and thermal/chemical stability. Therefore, to analyse the lattice structure and orientation of h-BN crystals becomes important. Here, the stacking order and wrinkles of h-BN are investigated by transmission electron microscopy (TEM). It is experimentally confirmed that the layers in the h-BN flakes are arranged in the AA' stacking. The wrinkles in a form of threefold network throughout the h-BN crystal are oriented along the armchair direction, and their formation mechanism was further explored by molecular dynamics simulations. Our findings provide a deep insight about the microstructure of h-BN and shed light on the structural design/electronic modulations of two-dimensional crystals.

cond-mat.mtrl-sci↗

arXiv2021

EMDS-5: Environmental Microorganism Image Dataset Fifth Version for Multiple Image Analysis Tasks

Environmental Microorganism Data Set Fifth Version (EMDS-5) is a microscopic image dataset including original Environmental Microorganism (EM) images and two sets of Ground Truth (GT) images. The GT image sets include a single-object GT image set and a multi-object GT image set. The EMDS-5 dataset has 21 types of EMs, each of which contains 20 original EM images, 20 single-object GT images and 20 multi-object GT images. EMDS-5 can realize to evaluate image preprocessing, image segmentation, feature extraction, image classification and image retrieval functions. In order to prove the effectiveness of EMDS-5, for each function, we select the most representative algorithms and price indicators for testing and evaluation. The image preprocessing functions contain two parts: image denoising and image edge detection. Image denoising uses nine kinds of filters to denoise 13 kinds of noises, respectively. In the aspect of edge detection, six edge detection operators are used to detect the edges of the images, and two evaluation indicators, peak-signal to noise ratio and mean structural similarity, are used for evaluation. Image segmentation includes single-object image segmentation and multi-object image segmentation. Six methods are used for single-object image segmentation, while k-means and U-net are used for multi-object segmentation.We extract nine features from the images in EMDS-5 and use the Support Vector Machine classifier for testing. In terms of image classification, we select the VGG16 feature to test different classifiers. We test two types of retrieval approaches: texture feature retrieval and deep learning feature retrieval. We select the last layer of features of these two deep learning networks as feature vectors. We use mean average precision as the evaluation index for retrieval.

cs.CV↗

arXiv2021

Extension of the Generalized Hydrodynamics to the Dimensional Crossover Regime

In an effort to address integrability breaking in cold gas experiments, we extend the integrable hydrodynamics of the 1d Lieb-Liniger model with two additional components representing the population of atoms in the first and second transverse excited states, thus enabling a description of quasi-1d condensates. Collisions between different components are accounted for through the inclusion of a Boltzmann-type collision integral in the hydrodynamic equation. Contrary to standard generalized hydrodynamics, our extended model captures thermalization of the condensate at a rate consistent with experimental observations from a quantum Newton's cradle setup.

cond-mat.quant-gas↗

arXiv2021

Interfacial Electron-Phonon Coupling Constants Extracted from Intrinsic Replica Bands in Monolayer FeSe/SrTiO$_3$

The observation of replica bands by angle-resolved photoemission spectroscopy has ignited interest in the study of electron-phonon coupling at low carrier densities, particularly in monolayer FeSe/SrTiO$_3$, where the appearance of replica bands has motivated theoretical work suggesting that the interfacial coupling of electrons in the FeSe layer to optical phonons in the SrTiO$_3$ substrate might contribute to the enhanced superconducting pairing temperature. Alternatively, it has also been recently proposed that such replica bands might instead originate from extrinsic final state losses associated with the photoemission process. Here, we perform a quantitative examination of replica bands in monolayer FeSe/SrTiO$_3$, where we are able to conclusively demonstrate that the replica bands are indeed signatures of intrinsic electron-boson coupling, and not associated with final state effects. A detailed analysis of the energy splittings between the higher-order replicas, as well as other self-energy effects, allow us to determine that the interfacial electron-phonon coupling in the system corresponds to a value of $λ= 0.19 \pm 0.02$.

cond-mat.mtrl-sci↗

arXiv2021

Cocktail Edge Caching: Ride Dynamic Trends of Content Popularity with Ensemble Learning

Edge caching will play a critical role in facilitating the emerging content-rich applications. However, it faces many new challenges, in particular, the highly dynamic content popularity and the heterogeneous caching configurations. In this paper, we propose Cocktail Edge Caching, that tackles the dynamic popularity and heterogeneity through ensemble learning. Instead of trying to find a single dominating caching policy for all the caching scenarios, we employ an ensemble of constituent caching policies and adaptively select the best-performing policy to control the cache. Towards this goal, we first show through formal analysis and experiments that different variations of the LFU and LRU policies have complementary performance in different caching scenarios. We further develop a novel caching algorithm that enhances LFU/LRU with deep recurrent neural network (LSTM) based time-series analysis. Finally, we develop a deep reinforcement learning agent that adaptively combines base caching policies according to their virtual hit ratios on parallel virtual caches. Through extensive experiments driven by real content requests from two large video streaming platforms, we demonstrate that CEC not only consistently outperforms all single policies, but also improves the robustness of them. CEC can be well generalized to different caching scenarios with low computation overheads for deployment.

cs.NI↗

arXiv2021

Compact, all-PM fiber integrated and alignment-free ultrafast Yb:fiber NALM laser with sub-femtosecond timing jitter

We report a simple and compact design of a dispersion compensated mode-locked Yb:fiber oscillator based on a nonlinear amplifying loop mirror (NALM). The fully polarization maintaining (PM) fiber integrated laser features a chirped fiber Bragg grating (CFBG) for dispersion compensation and a fiber integrated compact non-reciprocal phase bias device, which is alignment-free. The main design parameters were determined by numerically simulating the pulse evolution in the oscillator and by analyzing their impact on the laser performance. Experimentally, we achieved an 88 fs compressed pulse duration with sub-fs timing jitter at 54 MHz repetition rate and 51 mW of output power with 5.5 * 10-5 [20 Hz, 1 MHz] integrated relative intensity noise (RIN). Furthermore, we demonstrate tight phase-locking of the laser's carrier-envelope offset frequency (fceo) to a stable radio frequency (RF) reference and of one frequency comb tooth to a stable optical reference at 291 THz.

physics.optics↗

arXiv2020

Automatic Summarization of Open-Domain Podcast Episodes

We present implementation details of our abstractive summarizers that achieve competitive results on the Podcast Summarization task of TREC 2020. A concise textual summary that captures important information is crucial for users to decide whether to listen to the podcast. Prior work focuses primarily on learning contextualized representations. Instead, we investigate several less-studied aspects of neural abstractive summarization, including (i) the importance of selecting important segments from transcripts to serve as input to the summarizer; (ii) striking a balance between the amount and quality of training instances; (iii) the appropriate summary length and start/end points. We highlight the design considerations behind our system and offer key insights into the strengths and weaknesses of neural abstractive systems. Our results suggest that identifying important segments from transcripts to use as input to an abstractive summarizer is advantageous for summarizing long documents. Our best system achieves a quality rating of 1.559 judged by NIST evaluators---an absolute increase of 0.268 (+21%) over the creator descriptions.

cs.CL↗

arXiv2020

The study of multi-peaked type-I X-ray bursts in the neutron-star low mass X-ray binary 4U 1636$-$536 with RXTE

We have found and analysed 16 multi-peaked type-I bursts from the neutron-star low mass X-ray binary 4U 1636$-$53 with the Rossi X-ray Timing Explorer (RXTE). One of the bursts is a rare quadruple-peaked burst which was not previously reported. All 16 bursts show a multi-peaked structure not only in the X-ray light curves but also in the bolometric light curves. Most of the multi-peaked bursts appear in observations during the transition from the hard to the soft state in the colour-colour diagram. We find an anti-correlation between the second peak flux and the separation time between two peaks. We also find that in the double-peaked bursts the peak-flux ratio and the temperature of the thermal component in the pre-burst spectra are correlated. This indicates that the double-peaked structure in the light curve of the bursts may be affected by enhanced accretion rate in the disc, or increased temperature of the neutron star.

astro-ph.HE↗

arXiv2020

Simulation of Quantum Computing on Classical Supercomputers

Simulation of quantum computing on supercomputers is a significant research topic, which plays a vital role in quantum algorithm verification, error-tolerant verification and other applications. Tensor network contraction based on density matrix is an important single-amplitude simulation strategy, but it is hard to execute on the distributed computing systems currently. In this paper, we dive deep into this problem, and propose a scheme based on cutting edges of undirected graphs. This scheme cuts edges of undirected graphs with large tree width to obtain many undirected subgraphs with small tree width, and these subgraphs contracted on different computing cores. The contraction results of slave cores are summarized in the master node, which is consistent with the original tensor network contraction. Thus, we can simulate the larger scale quantum circuit than single core. Moreover, it's an NP-hard problem to find the global optimum cutting edges, and we propose a search strategy based on a heuristic algorithm to approach it. In order to verify the effectiveness of our scheme, we conduct tests based on QAOA algorithm, and it can simulate 120-qubit 3-regular QAOA algorithm on 4096-core supercomputer, which greatly exceeds the simulation scale on a single core of 100-qubit.

quant-ph↗

arXiv2020

Relaxation of Bosons in One Dimension and the Onset of Dimensional Crossover

We study ultra-cold bosons out of equilibrium in a one-dimensional (1D) setting and probe the breaking of integrability and the resulting relaxation at the onset of the crossover from one to three dimensions. In a quantum Newton's cradle type experiment, we excite the atoms to oscillate and collide in an array of 1D tubes and observe the evolution for up to 4.8 seconds (400 oscillations) with minimal heating and loss. By investigating the dynamics of the longitudinal momentum distribution function and the transverse excitation, we observe and quantify a two-stage relaxation process. In the initial stage single-body dephasing reduces the 1D densities, thus rapidly drives the 1D gas out of the quantum degenerate regime. The momentum distribution function asymptotically approaches the distribution of quasimomenta (rapidities), which are conserved in an integrable system. In the subsequent long time evolution, the 1D gas slowly relaxes towards thermal equilibrium through the collisions with transversely excited atoms. Moreover, we tune the dynamics in the dimensional crossover by initializing the evolution with different imprinted longitudinal momenta (energies). The dynamical evolution towards the relaxed state is quantitatively described by a semiclassical molecular dynamics simulation.

cond-mat.quant-gas↗

arXiv2020

Better Highlighting: Creating Sub-Sentence Summary Highlights

Amongst the best means to summarize is highlighting. In this paper, we aim to generate summary highlights to be overlaid on the original documents to make it easier for readers to sift through a large amount of text. The method allows summaries to be understood in context to prevent a summarizer from distorting the original meaning, of which abstractive summarizers usually fall short. In particular, we present a new method to produce self-contained highlights that are understandable on their own to avoid confusion. Our method combines determinantal point processes and deep contextualized representations to identify an optimal set of sub-sentence segments that are both important and non-redundant to form summary highlights. To demonstrate the flexibility and modeling power of our method, we conduct extensive experiments on summarization datasets. Our analysis provides evidence that highlighting is a promising avenue of research towards future summarization.

cs.CL↗