arXiv subjects

Chao Dong

Publications and source records attributed to Chao Dong.

At least 163 records · Page 9Linked to original sources

arXiv2021

Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression

Recent works have shown that learned models can achieve significant performance gains, especially in terms of perceptual quality measures, over traditional methods. Hence, the state of the art in image restoration and compression is getting redefined. This special issue covers the state of the art in learned image/video restoration and compression to promote further progress in innovative architectures and training methods for effective and efficient networks for image/video restoration and compression.

eess.IV↗

arXiv2021

Attentive Representation Learning with Adversarial Training for Short Text Clustering

Short text clustering has far-reaching effects on semantic analysis, showing its importance for multiple applications such as corpus summarization and information retrieval. However, it inevitably encounters the severe sparsity of short text representations, making the previous clustering approaches still far from satisfactory. In this paper, we present a novel attentive representation learning model for shot text clustering, wherein cluster-level attention is proposed to capture the correlations between text representations and cluster representations. Relying on this, the representation learning and clustering for short texts are seamlessly integrated into a unified model. To further ensure robust model training for short texts, we apply adversarial training to the unsupervised clustering setting, by injecting perturbations into the cluster representations. The model parameters and perturbations are optimized alternately through a minimax game. Extensive experiments on four real-world short text datasets demonstrate the superiority of the proposed model over several strong competitors, verifying that robust adversarial training yields substantial performance gains.

cs.LG↗

arXiv2021

Magnetized Rutherford scattering angle for electron-ion collision in plasma

Rutherford scattering formula plays an important role in plasma classical transport. It is urgent to need a magnetized Rutherford scattering formula since the magnetic field increases significantly in different fusion areas (e.g. tokamak magnetic field, self-generated magnetic field, and compressed magnetic field). The electron-ion Coulomb collisions perpendicular to the external magnetic field are studied in this paper. The scattering angle is defined according to the electron trajectory and asymptotic line (without magnetic field). A magnetized Rutherford scattering formula is obtained analytically under the weak magnetic field approximation. It is found that the scattering angle decreases as external magnetic field increases. It is easy to find the scattering angle decreasing significantly as incident distance, and incident velocity increasing. It is shown that the theoretical results agree well with numerical calculation by checking the dependence of scattering angle on external magnetic field.

physics.plasm-ph↗

arXiv2020

Medium-temperature furnace bake of Superconducting Radio-Frequency cavities at IHEP

Recently, heat treatment between 250 C and 500 C has been attempted to improve quality factor of superconducting radio-frequency cavities at FNAL and KEK. Experiments of such medium temperature (mid-T) bake with furnaces have also been carried out at IHEP. Firstly, eleven 1.3 GHz 1-cell cavities were treated with different temperatures at a small furnace. The average quality factor has reached 3.6E10 when the gradient is 16 MV/m. Then, the recipe of mid-T furnace bake at 300 C for 3 hours has been applied to six 1.3 GHz 9-cell cavities at a new big furnace. The average quality factor has reached 3.8E10 when the gradient is 16 MV/m.

physics.acc-ph↗

arXiv2020

High-resolution Calorimetry in Pulsed Magnetic Fields

We have developed a new calorimeter for measuring thermodynamic properties in pulsed magnetic fields. An instrumental design is described along with the construction details including the sensitivity of a RuO2 thermometer. The operation of the calorimeter is demonstrated by measuring heat capacity of three samples, pure Germanium, CeCu2Ge2, and $κ$-(BEDT-TTF)2Cu[N(CN)2]Br, in pulsed fields up to 43.5 T. We have found that realization of field-stability is a key for measuring high-resolution heat capacity under pulsed fields. We have also tested the performance of the calorimeter by employing two measurement techniques; the quasi-adiabatic and dual-slope methods. We demonstrate that the calorimeter developed in this study is capable of performing high-resolution calorimetry in pulsed magnetic fields, which opens new opportunities for high-field thermodynamic studies.

physics.ins-det↗

arXiv2020

Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent perceptual IR algorithms based on generative adversarial networks (GANs) have brought in significant improvement on visual performance, but also pose great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. We present two questions: Can existing IQA methods objectively evaluate recent IR algorithms? With the focus on beating current benchmarks, are we getting better IR algorithms? To answer the questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing ALgorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based IR algorithms, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable Elo system. Based on PIPAL, we present new benchmarks for both IQA and SR methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we shed light on how to improve the IQA performance on GAN-based distortion. Inspired by the find that the existing IQA methods have an unsatisfactory performance on the GAN-based distortion partially because of their low tolerance to spatial misalignment, we propose to improve the performance of an IQA network on GAN-based distortion by explicitly considering this misalignment. We propose the Space Warping Difference Network, which includes the novel l_2 pooling layers and Space Warping Difference layers. Experiments demonstrate the effectiveness of the proposed method.

eess.IV↗

arXiv2020

Efficient Image Super-Resolution Using Pixel Attention

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one - SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its twobranch architecture and attention scheme. While the second one - UPA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model- PAN could achieve similar performance as the lightweight networks - SRResNet and CARN, but with only 272K parameters (17.92% of SRResNet and 17.09% of CARN). The effectiveness of each proposed component is also validated by ablation study. The code is available at https://github.com/zhaohengyuan1/PAN.

eess.IV↗

arXiv2020

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based methods, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method.

eess.IV↗

arXiv2020

Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

Interactive image restoration aims to generate restored images by adjusting a controlling coefficient which determines the restoration level. Previous works are restricted in modulating image with a single coefficient. However, real images always contain multiple types of degradation, which cannot be well determined by one coefficient. To make a step forward, this paper presents a new problem setup, called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels. Compared with the previous single-dimension (SD) modulation, the MD is setup to handle multiple degradations adaptively and relief unbalanced learning problem in different degradations. We also propose a deep architecture - CResMD with newly introduced controllable residual connections for multi-dimension modulation. Specifically, we add a controlling variable on the conventional residual connection to allow a weighted summation of input and residual. The values of these weights are generated by another condition network. We further propose a new data sampling strategy based on beta distribution to balance different degradation types and levels. With corrupted image and degradation information as inputs, the network can output the corresponding restored image. By tweaking the condition vector, users can control the output effects in MD space at test time. Extensive experiments demonstrate that the proposed CResMD achieve excellent performance on both SD and MD modulation tasks. Code is available at https://github.com/hejingwenhejingwen/CResMD.

eess.IV↗

arXiv2020

Conditional Sequential Modulation for Efficient Global Image Retouching

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of $1\times1$ convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://github.com/hejingwenhejingwen/CSRNet.

cs.CV↗

arXiv2020

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution.

eess.IV↗

arXiv2020

Understanding Deformable Alignment in Video Super-Resolution

Deformable convolution, originally proposed for the adaptation to geometric variations of objects, has recently shown compelling performance in aligning multiple frames and is increasingly adopted for video super-resolution. Despite its remarkable performance, its underlying mechanism for alignment remains unclear. In this study, we carefully investigate the relation between deformable alignment and the classic flow-based alignment. We show that deformable convolution can be decomposed into a combination of spatial warping and convolution. This decomposition reveals the commonality of deformable alignment and flow-based alignment in formulation, but with a key difference in their offset diversity. We further demonstrate through experiments that the increased diversity in deformable alignment yields better-aligned features, and hence significantly improves the quality of video super-resolution output. Based on our observations, we propose an offset-fidelity loss that guides the offset learning with optical flow. Experiments show that our loss successfully avoids the overflow of offsets and alleviates the instability problem of deformable alignment. Aside from the contributions to deformable alignment, our formulation inspires a more flexible approach to introduce offset diversity to flow-based alignment, improving its performance.

cs.CV↗

arXiv2020

Enhanced Quadratic Video Interpolation

With the prosperity of digital video industry, video frame interpolation has arisen continuous attention in computer vision community and become a new upsurge in industry. Many learning-based methods have been proposed and achieved progressive results. Among them, a recent algorithm named quadratic video interpolation (QVI) achieves appealing performance. It exploits higher-order motion information (e.g. acceleration) and successfully models the estimation of interpolated flow. However, its produced intermediate frames still contain some unsatisfactory ghosting, artifacts and inaccurate motion, especially when large and complex motion occurs. In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model. In particular, we adopt a rectified quadratic flow prediction (RQFP) formulation with least squares method to estimate the motion more accurately. Complementary with image pixel-level blending, we introduce a residual contextual synthesis network (RCSN) to employ contextual information in high-dimensional feature space, which could help the model handle more complicated scenes and motion patterns. Moreover, to further boost the performance, we devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process. The proposed EQVI model won the first place in the AIM2020 Video Temporal Super-Resolution Challenge.

cs.CV↗

arXiv2020

Strain-tunable magnetism and nodal loops in monolayer MnB

Designing two-dimensional (2D) materials with magnetic and topological properties has continuously attracted intense interest in fundamental science and potential applications. Here, on the basis of first-principles calculations, we predict the coexistence of antiferromagnetism and Dirac nodal loop (NL) in the monolayer MnB, where the band crossing points are very close to the Fermi Level. Remarkably, a moderate strain can induce an antiferromagnetic to ferromagnetic phase transition, driving the monolayer MnB to a ferromagnetic metal with Weyl NLs. Such a type of topological quantum phase transition has not been observed before. In addition, the symmetry-protected properties of the two types of NLs as well as the magnetic critical temperatures are investigated. The controllable magnetic and topological order in monolayer MnB offers a unique platform for exploring topological quantum phase transitions and realizing nanospintronic devices.

cond-mat.mtrl-sci↗

arXiv2020

Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution

Multi-scale techniques have achieved great success in a wide range of computer vision tasks. However, while this technique is incorporated in existing works, there still lacks a comprehensive investigation on variants of multi-scale convolution in image super resolution. In this work, we present a unified formulation over widely-used multi-scale structures. With this framework, we systematically explore the two factors of multi-scale convolution -- feature propagation and cross-scale communication. Based on the investigation, we propose a generic and efficient multi-scale convolution unit -- Multi-Scale cross-Scale Share-weights convolution (MS$^3$-Conv). Extensive experiments demonstrate that the proposed MS$^3$-Conv can achieve better SR performance than the standard convolution with less parameters and computational cost. Beyond quantitative analysis, we comprehensively study the visual quality, which shows that MS$^3$-Conv behave better to recover high-frequency details.

eess.IV↗

arXiv2020

UAVs as a Service: Boosting Edge Intelligence for Air-Ground Integrated Networks

The air-ground integrated network is a key component of future sixth generation (6G) networks to support seamless and near-instant super-connectivity. There is a pressing need to intelligently provision various services in 6G networks, which however is challenging. To meet this need, in this article, we propose a novel architecture called UaaS (UAVs as a Service) for the air-ground integrated network, featuring UAV as a key enabler to boost edge intelligence with the help of machine learning (ML) techniques. We envision that the proposed UaaS architecture could intelligently provision wireless communication service, edge computing service, and edge caching service by a network of UAVs, making full use of UAVs' flexible deployment and diverse ML techniques. We also conduct a case study where UAVs participate in the model training of distributed ML among multiple terrestrial users, whose result shows that the model training is efficient with a negligible energy consumption of UAVs, compared to the flight energy consumption. Finally, we discuss the challenges and open research issues in the UaaS.

cs.NI↗

arXiv2020

Sphere Constraint based Enumeration Methods to Analyze the Minimum Weight Distribution of Polar Codes

In this paper, the minimum weight distributions (MWDs) of polar codes and concatenated polar codes are exactly enumerated according to the distance property of codewords. We first propose a sphere constraint based enumeration method (SCEM) to analyze the MWD of polar codes with moderate complexity. The SCEM exploits the distance property that all the codewords with the identical Hamming weight are distributed on a spherical shell. Then, based on the SCEM and the Plotkin's construction of polar codes, a sphere constraint based recursive enumeration method (SCREM) is proposed to recursively calculate the MWD with a lower complexity. Finally, we propose a parity-check SCEM (PC-SCEM) to analyze the MWD of concatenated polar codes by introducing the parity-check equations of outer codes. Moreover, due to the distance property of codewords, the proposed three methods can exactly enumerate all the codewords belonging to the MWD. The enumeration results show that the SCREM can enumerate the MWD of polar codes with code length up to $2^{14}$ and the PC-SCEM can be used to optimize CRC-polar concatenated codes.

cs.IT↗

arXiv2020

Polar-Slotted ALOHA over Slot Erasure Channels

In this paper, we design a new polar slotted ALOHA (PSA) protocol over the slot erasure channels, which uses polar coding to construct the identical slot pattern (SP) assembles within each active user and base station. A theoretical analysis framework for the PSA is provided. First, by using the packet-oriented operation for the overlap packets when they conflict in a slot interval, we introduce the packet-based polarization transform and prove that this transform is independent of the packet's length. Second, guided by the packet-based polarization, an SP assignment (SPA) method with the variable slot erasure probability (SEP) and a SPA method with a fixed SEP value are designed for the PSA scheme. Then, a packet-oriented successive cancellation (pSC) and a pSC list (pSCL) decoding algorithm are developed. Simultaneously, the finite-slots throughput bounds and the asymptotic throughput for the pSC algorithm are analyzed. The simulation results show that the proposed PSA scheme can achieve an improved throughput with the pSC/SCL decoding algorithm over the traditional repetition slotted ALOHA scheme.

cs.IT↗