arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 451 records · Page 25Linked to original sources

arXiv2021

Training Data Set Refinement for the Machine Learning Potential of Li-Si Alloys via Structural Similarity Analysis

Machine learning potential enables molecular dynamics simulations of systems beyond the capability of classical force fields. The traditional approach to develop structural sets for training machine learning potential typically generate a great number of redundant configurations, which will result in unnecessary computational costs. This work investigates the possibility of reducing redundancy in an initial data set containing 6183 configurations for a Li-Si machine learning potential. Starting from the initial data set, we constructed a series of subsets ranging from 25 to 1500 configurations by combining a structural similarity analysis algorithm and the farthest point sampling method. Results show that the machine learning potential trained from a data set containing 400 configurations can achieve an accuracy comparable to the one developed from the initial data set of 6183 configurations in describing potential energies, atomic forces, and structural properties of Li-Si systems. In addition, the redundancy reducing approach also demonstrates advantages over the classic stochastic method for constructing a concise training data set for Li-Si systems.

physics.comp-ph↗

arXiv2021

DeepCervix: A Deep Learning-based Framework for the Classification of Cervical Cells Using Hybrid Deep Feature Fusion Techniques

Cervical cancer, one of the most common fatal cancers among women, can be prevented by regular screening to detect any precancerous lesions at early stages and treat them. Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors. To improve the manual screening practice, machine learning (ML) and deep learning (DL) based computer-aided diagnostic (CAD) systems have been investigated widely to classify cervical pap cells. Most of the existing researches require pre-segmented images to obtain good classification results, whereas accurate cervical cell segmentation is challenging because of cell clustering. Some studies rely on handcrafted features, which cannot guarantee the classification stage's optimality. Moreover, DL provides poor performance for a multiclass classification task when there is an uneven distribution of data, which is prevalent in the cervical cell dataset. This investigation has addressed those limitations by proposing DeepCervix, a hybrid deep feature fusion (HDFF) technique based on DL to classify the cervical cells accurately. Our proposed method uses various DL models to capture more potential information to enhance classification performance. Our proposed HDFF method is tested on the publicly available SIPAKMED dataset and compared the performance with base DL models and the LF method. For the SIPAKMED dataset, we have obtained the state-of-the-art classification accuracy of 99.85%, 99.38%, and 99.14% for 2-class, 3-class, and 5-class classification. Moreover, our method is tested on the Herlev dataset and achieves an accuracy of 98.32% for binary class and 90.32% for 7-class classification.

eess.IV↗

arXiv2021

Direct Observation of Chiral Phonons by Inelastic X-ray Scattering

Phonon chirality has attracted intensive attention since it breaks the traditional cognition that phonons are linear propagating bosons. This new quasiparticle property has been extensively studied theoretically and experimentally. However, characterization of the phonon chirality throughout the full Brillouin zone is still not possible due to the lack of available experimental tools. In this work, phonon dispersion and chirality of tungsten carbide were investigated by millielectronvolt energy-resolution inelastic X-ray scattering. The atomistic calculation indicates that in-plane longitudinal and transverse acoustic phonons near K and K$^\prime$ points are circularly polarized due to the broken inversion symmetry. Anomalous inelastic X-ray scattering by these circularly polarized phonons was observed and attributed to their chirality. Our results show that inelastic X-ray scattering can be utilized to characterize phonon chirality in materials and suggest that a revision to the phonon scattering function is necessary.

cond-mat.mtrl-sci↗

arXiv2021

A Lightweight Music Texture Transfer System

Deep learning researches on the transformation problems for image and text have raised great attention. However, present methods for music feature transfer using neural networks are far from practical application. In this paper, we initiate a novel system for transferring the texture of music, and release it as an open source project. Its core algorithm is composed of a converter which represents sounds as texture spectra, a corresponding reconstructor and a feed-forward transfer network. We evaluate this system from multiple perspectives, and experimental results reveal that it achieves convincing results in both sound effects and computational performance.

cs.SD↗

arXiv2021

Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation

Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS), including single- and multi-stage process, has attracted large attention due to data labeling efficiency. In this paper, we propose to embed affinity learning of multi-stage approaches in a single-stage model. To be specific, we introduce an adaptive affinity loss to thoroughly learn the local pairwise affinity. As such, a deep neural network is used to deliver comprehensive semantic information in the training phase, whilst improving the performance of the final prediction module. On the other hand, considering the existence of errors in the pseudo labels, we propose a novel label reassign loss to mitigate over-fitting. Extensive experiments are conducted on the PASCAL VOC 2012 dataset to evaluate the effectiveness of our proposed approach that outperforms other standard single-stage methods and achieves comparable performance against several multi-stage methods.

cs.CV↗

arXiv2021

Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images

In this paper, we focus on the challenging multicategory instance segmentation problem in remote sensing images (RSIs), which aims at predicting the categories of all instances and localizing them with pixel-level masks. Although many landmark frameworks have demonstrated promising performance in instance segmentation, the complexity in the background and scale variability instances still remain challenging for instance segmentation of RSIs. To address the above problems, we propose an end-to-end multi-category instance segmentation model, namely Semantic Attention and Scale Complementary Network, which mainly consists of a Semantic Attention (SEA) module and a Scale Complementary Mask Branch (SCMB). The SEA module contains a simple fully convolutional semantic segmentation branch with extra supervision to strengthen the activation of interest instances on the feature map and reduce the background noise's interference. To handle the under-segmentation of geospatial instances with large varying scales, we design the SCMB that extends the original single mask branch to trident mask branches and introduces complementary mask supervision at different scales to sufficiently leverage the multi-scale information. We conduct comprehensive experiments to evaluate the effectiveness of our proposed method on the iSAID dataset and the NWPU Instance Segmentation dataset and achieve promising performance.

cs.CV↗

arXiv2021

A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Environmental Microorganism Images: from Convolutional Neural Networks to Visual Transformers

Nowadays, analysis of Transparent Environmental Microorganism Images (T-EM images) in the field of computer vision has gradually become a new and interesting spot. This paper compares different deep learning classification performance for the problem that T-EM images are challenging to analyze. We crop the T-EM images into 8 * 8 and 224 * 224 pixel patches in the same proportion and then divide the two different pixel patches into foreground and background according to ground truth. We also use four convolutional neural networks and a novel ViT network model to compare the foreground and background classification experiments. We conclude that ViT performs the worst in classifying 8 * 8 pixel patches, but it outperforms most convolutional neural networks in classifying 224 * 224 pixel patches.

cs.CV↗

arXiv2021

Giant Anisotropic in-Plane Thermal Conduction Induced by Anomalous Phonons in Nearly-Equilaterally Structured PdSe2

In two-dimensional materials, structure difference induces the difference in phonon dispersions, leading to the anisotropy of in-plane thermal transport. Here, we report an exceptional case in layered PdSe2, where the bonding, force constants, and lattice constants are nearly-equal along the in-plane crystallographic axis directions. The phonon dispersions show significant differences between the Gamma-X and Gamma-Y directions, leading to the anisotropy of in-plane thermal conductivity with a ratio up to 1.8. Such anisotropy is not only unexpected in equilaterally structured (in-plane) materials but also comparable to the record in the non-equilaterally structured material reported to date. By combining inelastic X-ray scattering and first-principles calculations, we attribute such anisotropy to the low-energy phonons along Gamma-X, in particular, their lower group velocities and "avoided-crossing" behavior. The different bucking structures between a- (zigzag-type) and b-axis (flat-type) are mainly responsible for the unique phonon dynamics properties of PdSe2. The present results illustrate the unusual thermal conduction mechanism of the equilaterally structured materials and provide valuable insights on thermal management in electronic devices.

cond-mat.mtrl-sci↗

arXiv2021

Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation

It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict limits: 1) access to internal specifications of source models is a must; and 2) pseudo labels should be clean during self-training, making critical tasks relying on semantic segmentation unreliable. Aiming at these pitfalls, this study develops a domain adaptive solution to semantic segmentation with pseudo label rectification (namely \textit{PR-SFDA}), which operates in two phases: 1) \textit{Confidence-regularized unsupervised learning}: Maximum squares loss applies to regularize the target model to ensure the confidence in prediction; and 2) \textit{Noise-aware pseudo label learning}: Negative learning enables tolerance to noisy pseudo labels in training, meanwhile positive learning achieves fast convergence. Extensive experiments have been performed on domain adaptive semantic segmentation benchmark, \textit{GTA5 $\to$ Cityscapes}. Overall, \textit{PR-SFDA} achieves a performance of 49.0 mIoU, which is very close to that of the state-of-the-art counterparts. Note that the latter demand accesses to the source model's internal specifications, whereas the \textit{PR-SFDA} solution needs none as a sharp contrast.

cs.CV↗

arXiv2021

Instance-based Vision Transformer for Subtyping of Papillary Renal Cell Carcinoma in Histopathological Image

Histological subtype of papillary (p) renal cell carcinoma (RCC), type 1 vs. type 2, is an essential prognostic factor. The two subtypes of pRCC have a similar pattern, i.e., the papillary architecture, yet some subtle differences, including cellular and cell-layer level patterns. However, the cellular and cell-layer level patterns almost cannot be captured by existing CNN-based models in large-size histopathological images, which brings obstacles to directly applying these models to such a fine-grained classification task. This paper proposes a novel instance-based Vision Transformer (i-ViT) to learn robust representations of histopathological images for the pRCC subtyping task by extracting finer features from instance patches (by cropping around segmented nuclei and assigning predicted grades). The proposed i-ViT takes top-K instances as input and aggregates them for capturing both the cellular and cell-layer level patterns by a position-embedding layer, a grade-embedding layer, and a multi-head multi-layer self-attention module. To evaluate the performance of the proposed framework, experienced pathologists are invited to selected 1162 regions of interest from 171 whole slide images of type 1 and type 2 pRCC. Experimental results show that the proposed method achieves better performance than existing CNN-based models with a significant margin.

cs.CV↗

arXiv2021

Decomposition Formula for the Wall Heat Flux of a Compressible Boundary Layer

Understanding the generation mechanism of the heating flux is essential for the design of hypersonic vehicles. We proposed a novel formula to decompose the heat flux coefficient into the contributions of different terms by integrating the conservative equation of the total energy. The reliability of the formula is well demonstrated by the direct numerical simulation results of a hypersonic transitional boundary layer. Through this formula, the exact process of the energy transport in the boundary layer can be explained and the dominant contributors to the heat flux can be explored, which are beneficial for the prediction of the heat and design of the thermal protection devices

physics.flu-dyn↗

arXiv2021

Matryoshka Phonon Twinning in alpha-GaN

Understanding lattice dynamics is crucial for effective thermal management in high-power electronic devices because phonons dominate thermal transport in most semiconductors. This study utilizes complementary inelastic X-ray and neutron scattering techniques and reports the temperature-dependent phonon dynamics of alpha-GaN, one of the most important third-generation power semiconductors. A prominent Matryoshka phonon dispersion is discovered with the scattering tools and confirmed by the first-principles calculations. Such Matryoshka twinning throughout the three-dimension reciprocal space is demonstrated to amplify the anharmonicity of the related phonon modes through creating abundant three-phonon scattering channels and cutting the phonon lifetime of affected modes by more than 50%. Such phonon topology effectively contributes to the reduction of the in-plane thermal transport, thus the anisotropic thermal conductivity of alpha-GaN. The results not only have significant implications for engineering the thermal performance and other phonon-related properties of alpha-GaN, but also offer valuable insights on the role of anomalous phonon topology in thermal transport of other technically important semiconductors.

cond-mat.mtrl-sci↗

arXiv2021

Nuclei Grading of Clear Cell Renal Cell Carcinoma in Histopathological Image by Composite High-Resolution Network

The grade of clear cell renal cell carcinoma (ccRCC) is a critical prognostic factor, making ccRCC nuclei grading a crucial task in RCC pathology analysis. Computer-aided nuclei grading aims to improve pathologists' work efficiency while reducing their misdiagnosis rate by automatically identifying the grades of tumor nuclei within histopathological images. Such a task requires precisely segment and accurately classify the nuclei. However, most of the existing nuclei segmentation and classification methods can not handle the inter-class similarity property of nuclei grading, thus can not be directly applied to the ccRCC grading task. In this paper, we propose a Composite High-Resolution Network for ccRCC nuclei grading. Specifically, we propose a segmentation network called W-Net that can separate the clustered nuclei. Then, we recast the fine-grained classification of nuclei to two cross-category classification tasks, based on two high-resolution feature extractors (HRFEs) which are proposed for learning these two tasks. The two HRFEs share the same backbone encoder with W-Net by a composite connection so that meaningful features for the segmentation task can be inherited for the classification task. Last, a head-fusion block is applied to generate the predicted label of each nucleus. Furthermore, we introduce a dataset for ccRCC nuclei grading, containing 1000 image patches with 70945 annotated nuclei. We demonstrate that our proposed method achieves state-of-the-art performance compared to existing methods on this large ccRCC grading dataset.

eess.IV↗

arXiv2021

Towards interpreting computer vision based on transformation invariant optimization

Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs. Visualization of learned representations helps we humans understand the vision of DNNs. In this work, visualized images that can activate the neural network to the target classes are generated by back-propagation method. Here, rotation and scaling operations are applied to introduce the transformation invariance in the image generating process, which we find a significant improvement on visualization effect. Finally, we show some cases that such method can help us to gain insight into neural networks.

cs.CV↗

arXiv2021

A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer

Image classification has achieved unprecedented advance with the the rapid development of deep learning. However, the classification of tiny object images is still not well investigated. In this paper, we first briefly review the development of Convolutional Neural Network and Visual Transformer in deep learning, and introduce the sources and development of conventional noises and adversarial attacks. Then we use various models of Convolutional Neural Network and Visual Transformer to conduct a series of experiments on the image dataset of tiny objects (sperms and impurities), and compare various evaluation metrics in the experimental results to obtain a model with stable performance. Finally, we discuss the problems in the classification of tiny objects and make a prospect for the classification of tiny objects in the future.

cs.CV↗

arXiv2021

Ultrafast MHz-rate burst-mode pump-probe laser for the FLASH FEL facility based on nonlinear compression of ps-level pulses from an Yb-amplifier chain

The Free-Electron Laser (FEL) FLASH offers the worldwide still unique capability to study ultrafast processes with high-flux, high-repetition rate XUV and soft X-ray pulses. The vast majority of experiments at FLASH are of pump-probe type. Many of them rely on optical ultrafast lasers. Here, a novel FEL facility laser is reported which combines high average power output from Yb:YAG amplifiers with spectral broadening in a Herriott-type multi-pass cell and subsequent pulse compression to sub-100 fs durations. Compared to other facility lasers employing optical parametric amplification, the new system comes with significantly improved noise figures, compactness, simplicity and power efficiency. Like FLASH, the optical laser operates with 10 Hz burst repetition rate. The bursts consist of 800 $μ$s long trains of up to 800 ultrashort pulses being synchronized to the FEL with femtosecond precision. In the experimental chamber, pulses with up to 50 $μ$J energy, 60 fs FWHM duration and 1 MHz rate at 1.03 $μ$m wavelength are available and can be adjusted by computer-control. Moreover, nonlinear polarization rotation is implemented to improve laser pulse contrast. First cross-correlation measurements with the FEL at the plane-grating monochromator photon beamline are demonstrated, exhibiting the suitability of the laser for user experiments at FLASH.

physics.optics↗

arXiv2021

A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis

Pathology image analysis is an essential procedure for clinical diagnosis of many diseases. To boost the accuracy and objectivity of detection, nowadays, an increasing number of computer-aided diagnosis (CAD) system is proposed. Among these methods, random field models play an indispensable role in improving the analysis performance. In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models. Firstly, we introduce the background of two random fields and pathology images. Secondly, we summarize the basic mathematical knowledge of MRFs and CRFs from modelling to optimization. Then, a thorough review of the recent research on the MRFs and CRFs of pathology images analysis is presented. Finally, we investigate the popular methodologies in the related works and discuss the method migration among CAD field.

cs.CV↗

arXiv2021

PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demonstrated strong performances on natural language understanding and generation with \textit{few-shot in-context} learning. In this work, we present our practice on training large-scale autoregressive language models named PanGu-$α$, with up to 200 billion parameters. PanGu-$α$ is developed under the MindSpore and trained on a cluster of 2048 Ascend 910 AI processors. The training parallelism strategy is implemented based on MindSpore Auto-parallel, which composes five parallelism dimensions to scale the training task to 2048 processors efficiently, including data parallelism, op-level model parallelism, pipeline model parallelism, optimizer model parallelism and rematerialization. To enhance the generalization ability of PanGu-$α$, we collect 1.1TB high-quality Chinese data from a wide range of domains to pretrain the model. We empirically test the generation ability of PanGu-$α$ in various scenarios including text summarization, question answering, dialogue generation, etc. Moreover, we investigate the effect of model scales on the few-shot performances across a broad range of Chinese NLP tasks. The experimental results demonstrate the superior capabilities of PanGu-$α$ in performing various tasks under few-shot or zero-shot settings.

cs.CL↗