Searcharxiv⌕ Search

arXiv subjects

Chao Li

Publications and source records attributed to Chao Li.

At least 487 records · Page 27Linked to original sources
arXiv2020

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

eess.IV↗
arXiv2020

Single Image Reflection Removal through Cascaded Refinement

We address the problem of removing undesirable reflections from a single image captured through a glass surface, which is an ill-posed, challenging but practically important problem for photo enhancement. Inspired by iterative structure reduction for hidden community detection in social networks, we propose an Iterative Boost Convolutional LSTM Network (IBCLN) that enables cascaded prediction for reflection removal. IBCLN is a cascaded network that iteratively refines the estimates of transmission and reflection layers in a manner that they can boost the prediction quality to each other, and information across steps of the cascade is transferred using an LSTM. The intuition is that the transmission is the strong, dominant structure while the reflection is the weak, hidden structure. They are complementary to each other in a single image and thus a better estimate and reduction on one side from the original image leads to a more accurate estimate on the other side. To facilitate training over multiple cascade steps, we employ LSTM to address the vanishing gradient problem, and propose residual reconstruction loss as further training guidance. Besides, we create a dataset of real-world images with reflection and ground-truth transmission layers to mitigate the problem of insufficient data. Comprehensive experiments demonstrate that the proposed method can effectively remove reflections in real and synthetic images compared with state-of-the-art reflection removal methods.

cs.CV↗
arXiv2020

H-OWAN: Multi-distorted Image Restoration with Tensor 1x1 Convolution

It is a challenging task to restore images from their variants with combined distortions. In the existing works, a promising strategy is to apply parallel "operations" to handle different types of distortion. However, in the feature fusion phase, a small number of operations would dominate the restoration result due to the features' heterogeneity by different operations. To this end, we introduce the tensor 1x1 convolutional layer by imposing high-order tensor (outer) product, by which we not only harmonize the heterogeneous features but also take additional non-linearity into account. To avoid the unacceptable kernel size resulted from the tensor product, we construct the kernels with tensor network decomposition, which is able to convert the exponential growth of the dimension to linear growth. Armed with the new layer, we propose High-order OWAN for multi-distorted image restoration. In the numerical experiments, the proposed net outperforms the previous state-of-the-art and shows promising performance even in more difficult tasks.

cs.CV↗
arXiv2020

Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling

Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis. The numerical defects of TD methods, however, limit their practical applications on real-world data. As an alternative, convex tensor decomposition (CTD) was proposed to alleviate these problems, but its exact-recovery property is not properly addressed so far. To this end, we focus on latent convex tensor decomposition (LCTD), a practically widely-used CTD model, and rigorously prove a sufficient condition for its exact-recovery property. Furthermore, we show that such property can be also achieved by a more general model than LCTD. In the new model, we generalize the classic tensor (un-)folding into reshuffling operation, a more flexible mapping to relocate the entries of the matrix into a tensor. Armed with the reshuffling operations and exact-recovery property, we explore a totally novel application for (generalized) LCTD, i.e., image steganography. Experimental results on synthetic data validate our theory, and results on image steganography show that our method outperforms the state-of-the-art methods.

cs.LG↗
arXiv2020

Fine Deligne-Lusztig varieties and Arithmetic Fundamental Lemmas

We prove a character formula for some closed fine Deligne-Lusztig varieties. We apply it to compute fixed points for fine Deligne-Lusztig varieties arising from the basic loci of Shimura varieties of Coxeter type. As an application, we prove an arithmetic intersection formula for certain diagonal cycles on unitary and GSpin Rapoport-Zink spaces arising from the arithmetic Gan-Gross-Prasad conjectures. In particular, we prove the arithmetic fundamental lemma in the minuscule case, without assumptions on the residual characteristic.

math.NT↗
arXiv2020

Hierarchical hidden community detection for protein complex prediction

Motivation: Discovering functional modules in protein-protein interaction (PPI) networks by optimization methods remains a longstanding challenge in biology. Traditional algorithms simply consider strong protein complexes that can be found in the original network by optimizing some metrics, which causes obstacles for the discovery of weak and hidden complexes shielded by stronger complexes. Also, protein complexes are not only in different density but also in a large range of scale, making it extremely difficult to be detected. Toward this objective, we propose a hierarchical hidden community approach to predict protein complexes. Results: We propose a method called HirHide (Hierarchical Hidden Community Detection), which can be combined with traditional community detection methods to enable them to discover hierarchical hidden communities. It is the first community detection algorithm that can find a hierarchical structure as well as hidden structure. We compare the performance of three traditional methods with their HirHide versions. Experimental results show that the HirHide methods using traditional methods as the base algorithms achieve better performance, sometimes even significantly outperform the baselines.

q-bio.MN↗
arXiv2020

Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization

Hyperspectral super-resolution (HSR) fuses a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) to obtain a high-resolution HSI (HR-HSI). In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR. The proposed CTRF approach simultaneously learns high spectral resolution core tensor from the HSI and high spatial resolution core tensors from the MSI, and reconstructs the HR-HSI via tensor ring (TR) representation (Figure~\ref{fig:framework}). The CTRF model can separately exploit the low-rank property of each class (Section \ref{sec:analysis}), which has been never explored in the previous coupled tensor model. Meanwhile, it inherits the simple representation of coupled matrix/CP factorization and flexible low-rank exploration of coupled Tucker factorization. Guided by Theorem~\ref{th:1}, we further propose a spectral nuclear norm regularization to explore the global spectral low-rank property. The experiments have demonstrated the advantage of the proposed nuclear norm regularized CTRF (NCTRF) as compared to previous matrix/tensor and deep learning methods.

eess.IV↗
arXiv2019

High-Freedom Inverse Design with Deep Neural Network for Metasurface Filter in the Visible

In order to obtain a metasurface structure capable of filtering the light of a specific wavelength in the visible band, traditional method usually traverses the space consisting of possible designs, searching for a potentially satisfying device by performing iterative calculations to solve Maxwell's equations. In this paper, we propose a neural network that can complete an inverse design process to solve the problem. Compared with the traditional method, our method is much faster while competent of generating better devices with the desired spectrum. One of the most significant advantages is that it can handle a real spectrum as well as an artificial one. Besides, our method encompasses a high degree of freedom to generate devices, ensuring their generated spectra resemble desired ones and meeting the accuracy requirements without losing practicability in the manufacturing process.

cs.OH↗
arXiv2019

Gated Convolutional Networks with Hybrid Connectivity for Image Classification

We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual. Furthermore, SMG module is equipped with an efficient two-stage pipeline, which aims to DenseNet-like architectures that need to integrate all previous outputs, i.e., squeezing the incoming informative but redundant features gradually by hierarchical convolutions as a hourglass shape and then exciting it by multi-kernel depthwise convolutions, the output of which would be compact and hold more informative multi-scale features. We further develop a forget and an update gate by introducing the popular attention modules to implement the effective fusion instead of a simple addition between reused and new features. Due to the Hybrid Connectivity (nested combination of global dense and local residual) and Gated mechanisms, we called our network as the HCGNet. Experimental results on CIFAR and ImageNet datasets show that HCGNet is more prominently efficient than DenseNet, and can also significantly outperform state-of-the-art networks with less complexity. Moreover, HCGNet also shows the remarkable interpretability and robustness by network dissection and adversarial defense, respectively. On MS-COCO, HCGNet can consistently learn better features than popular backbones.

cs.CV↗
arXiv2019

Studies of the beam-ion instability and its mitigation with feedback system

The beam-ion interaction is a potential limitation of beam performance in electron accelerators, especially where the beam emittance is of a great concern in future ultra-low emittance light source. "Conventionally", the beam instability due to beam-ion interaction is attributed to two types of effects: ion trapping effect and fast ion effect, which emphasize the beam-ion dynamics in different time scales. Whereas, in accelerators, the beam suffers from a mixture of ion trapping effect and fast ion effect, leading to a more complicated process and requiring a self-consistent treatment. To evaluate the beam characteristics, as emittance growth under the influence from beam-ion effect, a new numerical simulation code based on the "quasi-strong-strong" model has been developed, including modules of ionization, beam-ion interaction, synchrotron radiation damping, quantum excitation, bunch-by-bunch feedback, etc. In the study, we do not regularly distinguish the ion trapping effect and the fast ion effect, but treat beam-ion interaction more generally and consistently. The lattice of High Energy Photon Source, a diffraction limit ring under construction in Beijing, is used as an example to show the beam-ion effect. It is found that in this low emittance ring, the beam-ion instability is not a dominant mechanism in operation mode with a high beam current, but seriously occurs in a lower beam current region. When the beam-ion instability were significantly driven and can not be damped by the synchrotron radiation damping, the simulations show the bunch-by-bunch feedback system based on the Finite Impulse Response filter technique can be adopted to mitigate it effectively.

physics.acc-ph↗
arXiv2019

Near source fluorescence spectroscopy for miniaturized thermal atomic beams

Miniature atomic beams can provide new functionalities for atom based sensing instruments such as atomic clocks and interferometers. We recently demonstrated a planar silicon device for generating well-collimated thermal atomic beams [Nat Commun 10, 1831 (2019)]. Here, we present a near-source fluorescence spectroscopy (NSFS) technique that can fully characterize such miniature beams even when measured only a few millimeters from the nozzle exit. We also present a recipe for predicting the fluorescence spectrum, and therefore, the source angular distribution, even under conditions of strong laser saturation of the probing transition. Monte Carlo simulations together with multi-level master equation calculations fully account for the influence of optical pumping and spatial extension of the Gaussian laser beam. A notable consequence of this work is the agreement between theory and experimental data that has allowed fine details of the angular distribution of the collimator to be resolved over 3 decades of dynamic range of atomic beam output flux.

physics.atom-ph↗
arXiv2019

On the 2-part of the Birch and Swinnerton-Dyer conjecture for quadratic twists of elliptic curves

In the present paper, we prove, for a large class of elliptic curves defined over $\mathbb{Q}$, the existence of an explicit infinite family of quadratic twists with analytic rank $0$. In addition, we establish the $2$-part of the conjecture of Birch and Swinnerton-Dyer for many of these infinite families of quadratic twists. Recently, Xin Wan has used our results to prove for the first time the full Birch--Swinnerton-Dyer conjecture for some explicit infinite families of elliptic curves defined over $\mathbb{Q}$ without complex multiplication.

math.NT↗
arXiv2019

Possibility to construct a clock on non 0-0 transition

In this letter, we discuss the possibility of non 0-0 atomic lines as the reference transitions to design a new atomic clock. The proposed clock operates in high C-field regime offering an interesting alternative to conventional clock based on 0-0 transition as the former can also eliminate the influence of the first-order Zeeman effect. Using the Breit-Rabi formula, we theoretically calculate the magnetically insensitive frequency and the corresponding C-field value for different alkali atom species. We also provide an estimate of the uncertainty of frequency shift to change of C-field. We show that a high C-field clock based on Cs: 3,-1 - 4,0, 3,0 - 4,-1, and 3,-1 - 4,-1, can achieve a bias of 10-14 with a C-field of 10-6 uncertainty. The free first-order Zeeman effect C-field for 3,-1 - 4,0 or 3,0 - 4,-1 transition is about one half that for 3,-1 - 4,-1 transition.

physics.atom-ph↗
arXiv2019

TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation

In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story. This differs from traditional video highlight detection or video summarization problems in that each sub-video is required to maintain a coherent and integral story, which is becoming particularly important for resource-production video sharing platforms such as Youtube, Facebook, TikTok, Kwai, etc. To address the problem, we collect and annotate a new large video truncation dataset, named as TruNet, which contains 1470 videos with on average 11 short stories per video. With the new dataset, we further develop and train a neural architecture for video truncation that consists of two components: a Boundary Aware Network (BAN) and a Fast-Forward Long Short-Term Memory (FF-LSTM). We first use the BAN to generate high quality temporal proposals by jointly considering frame-level attractiveness and boundaryness. We then apply the FF-LSTM, which tends to capture high-order dependencies among a sequence of frames, to decide whether a temporal proposal is a coherent and integral story. We show that our proposed framework outperforms existing approaches for the story-preserving long video truncation problem in both quantitative measures and user-study. The dataset is available for public academic research usage at https://ai.baidu.com/broad/download.

cs.CV↗
arXiv2019

Measurements of differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li reaction in the neutron energy range from 1.0 eV to 2.5 MeV

Differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li, $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions have been measured at CSNS Back-n white neutron source. Two enriched (90%) $^{10}$B samples 5.0 cm in diameter and ~85.0 $μ$g/cm$^{2}$ in thickness each with an aluminum backing were prepared, and back-to-back mounted at the sample holder. The charged particles were detected using the silicon-detector array of the Light-charged Particle Detector Array (LPDA) system. The neutron energy E$_{n}$ was determined by TOF (time-of-flight) method, and the valid $α$ events were extracted from the E$_{n}$-Amplitude two-dimensional spectrum. With 15 silicon detectors, the differential cross sections of $α$-particles were measured from 19.2° to 160.8°. Fitted with the Legendre polynomial series, the ($n, α$) cross sections were obtained through integration. The absolute cross sections were normalized using the standard cross sections of the $^{10}$B($n, α$)$^{7}$Li reaction in the 0.3 - 0.5 MeV neutron energy region. The measurement neutron energy range for the $^{10}$B($n, α$)$^{7}$Li reaction is 1.0 eV $\le$ En < 2.5 MeV (67 energy points), and for the $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions is 1.0 eV $\le$ En < 1.0 MeV (59 energy points). The present results have been analyzed by the resonance reaction mechanism and the level structure of the $^{11}$B compound system, and compared with existing measurements and evaluations.

nucl-ex↗
arXiv2019

On a conjecture about a class of permutation quadrinomials

Very recently, Tu et al. presented a sufficient condition about $(a_1,a_2,a_3)$, see Theorem 1.1, such that $f(x) = x^{3\cdot 2^m} + a_1 x^{2^{m+1}+1}+ a_2 x^{2^m+2} + a_3 x^3$ is a class of permutation polynomials over $\gf_{2^{n}}$ with $n=2m$ and $m$ odd. In this present paper, we prove that the sufficient condition is also necessary.

cs.IT↗
arXiv2019

Image Inpainting with Learnable Bidirectional Attention Maps

Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness. Partial convolution has been suggested to address this issue, but it adopts handcrafted feature re-normalization, and only considers forward mask-updating. In this paper, we present a learnable attention map module for learning feature renormalization and mask-updating in an end-to-end manner, which is effective in adapting to irregular holes and propagation of convolution layers. Furthermore, learnable reverse attention maps are introduced to allow the decoder of U-Net to concentrate on filling in irregular holes instead of reconstructing both holes and known regions, resulting in our learnable bidirectional attention maps. Qualitative and quantitative experiments show that our method performs favorably against state-of-the-arts in generating sharper, more coherent and visually plausible inpainting results. The source code and pre-trained models will be available.

cs.CV↗