arXiv subjects

Xiumei Wang

Publications and source records attributed to Xiumei Wang.

46 records · Page 3Linked to original sources

arXiv2019

AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results

This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results. The challenge had 3 tracks. Taking the three main aspects (i.e., number of parameters, inference/running time, fidelity (PSNR)) of MSRResNet as the baseline, Track 1 aims to reduce the amount of parameters while being constrained to maintain or improve the running time and the PSNR result, Tracks 2 and 3 aim to optimize running time and PSNR result with constrain of the other two aspects, respectively. Each track had an average of 64 registered participants, and 12 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

eess.IV↗

arXiv2019

Lightweight Image Super-Resolution with Information Multi-distillation Network

In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results. Thanks to the powerful representation capabilities of the deep networks, numerous previous ways can learn the complex non-linear mapping between low-resolution (LR) image patches and their high-resolution (HR) versions. However, excessive convolutions will limit the application of super-resolution technology in low computing power devices. Besides, super-resolution of any arbitrary scale factor is a critical issue in practical applications, which has not been well solved in the previous approaches. To address these issues, we propose a lightweight information multi-distillation network (IMDN) by constructing the cascaded information multi-distillation blocks (IMDB), which contains distillation and selective fusion parts. Specifically, the distillation module extracts hierarchical features step-by-step, and fusion module aggregates them according to the importance of candidate features, which is evaluated by the proposed contrast-aware channel attention mechanism. To process real images with any sizes, we develop an adaptive cropping strategy (ACS) to super-resolve block-wise image patches using the same well-trained model. Extensive experiments suggest that the proposed method performs favorably against the state-of-the-art SR algorithms in term of visual quality, memory footprint, and inference time. Code is available at \url{https://github.com/Zheng222/IMDN}.

eess.IV↗

arXiv2019

Birkhoff-von Neumann Graphs that are PM-compact

A well-studied geometric object in combinatorial optimization is the perfect matching polytope of a graph $G$. In any investigation concerning the perfect matching polytope, one may assume that $G$ is matching covered --- that is, it is a connected graph (of order at least two) and each edge lies in some perfect matching. A graph $G$ is Birkhoff-von Neumann (BvN) if its perfect matching polytope is characterized solely by non-negativity and degree constraints. A result of Balas (1981) implies that $G$ is BvN if and only if $G$ does not contain a pair of vertex-disjoint odd cycles $(C_1,C_2)$ such that $G-V(C_1)-V(C_2)$ has a perfect matching. It follows immediately that the corresponding decision problem is in co-NP. However, it is not known to be in NP. The problem is in P if the input graph is planar --- due to a result of Carvalho, Lucchesi and Murty (2004). These authors, along with Kothari (2018), have shown that this problem is equivalent to the seemingly unrelated problem of deciding whether a given graph is $\overline{C_6}$-free. The combinatorial diameter of a polytope is the diameter of its $1$-skeleton graph. A graph $G$ is PM-compact (PMc) if the combinatorial diameter of its perfect matching polytope equals one. A result of Chvátal (1975) implies that $G$ is PMc if and only if $G$ does not contain a pair of vertex-disjoint even cycles $(C_1,C_2)$ such that $G-V(C_1)-V(C_2)$ has a perfect matching. Once again the corresponding decision problem is in co-NP, but it is not known to be in NP. The problem is in P if the input graph is bipartite or is near-bipartite --- due to a result of Wang, Lin, Carvalho, Lucchesi, Sanjith and Little (2013). In this paper, we consider the "intersection" of the aforementioned problems. We give a complete characterization of matching covered graphs that are BvN as well as PMc. (Thus the corresponding decision problem is in P.)

math.CO↗

arXiv2018

PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report

This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, participants were solving the classical image super-resolution problem with a bicubic downscaling factor of 4. The second track was aimed at real-world photo enhancement, and the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with a DSLR camera. The target metric used in this challenge combined the runtime, PSNR scores and solutions' perceptual results measured in the user study. To ensure the efficiency of the submitted models, we additionally measured their runtime and memory requirements on Android smartphones. The proposed solutions significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.

cs.CV↗

arXiv2018

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution. However, as the depth and width of the networks increase, CNN-based super-resolution methods have been faced with the challenges of computational complexity and memory consumption in practice. In order to solve the above questions, we propose a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image. In general, the proposed model consists of three parts, which are feature extraction block, stacked information distillation blocks and reconstruction block respectively. By combining an enhancement unit with a compression unit into a distillation block, the local long and short-path features can be effectively extracted. Specifically, the proposed enhancement unit mixes together two different types of features and the compression unit distills more useful information for the sequential blocks. In addition, the proposed network has the advantage of fast execution due to the comparatively few numbers of filters per layer and the use of group convolution. Experimental results demonstrate that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.

cs.CV↗

arXiv2018

Three matching intersection property for matching covered graphs

In connection with Fulkerson's conjecture on cycle covers, Fan and Raspaud proposed a weaker conjecture: For every bridgeless cubic graph $G$, there are three perfect matchings $M_1$, $M_2$, and $M_3$ such that $M_1\cap M_2 \cap M_3=\emptyset$. We call the property specified in this conjecture the three matching intersection property (and 3PM property for short). We study this property on matching covered graphs. The main results are a necessary and sufficient condition and its applications to characterization of special graphs, such as the Halin graphs and 4-regular graphs.

math.CO↗

arXiv2016

A note on Matching Cover Algorithm

A $k$-matching cover of a graph $G$ is a union of $k$ matchings of $G$ which covers $V(G)$. A matching cover of $G$ is optimal if it consists of the fewest matchings of $G$. In this paper, we present an algorithm for finding an optimal matching cover of a graph on $n$ vertices and $m$ edges in $O(nm)$ time. This algorithm corrects an error of Matching Cover Algorithm in (Xiumei Wang, Xiaoxin Song, Jinjiang Yuan, On matching cover of graphs, Math. Program. Ser. A (2014)147: 499-518).

math.CO↗

arXiv2016

Improvement in medium-long term frequency stability of integrating sphere cold atom clock

The medium-long term frequency stability of the integrating sphere cold atom clock was improved.During the clock operation, Rb atoms were cooled and manipulated using cooling light diffusely reflected by the inner surface of a microwave cavity in the clock. This light heated the cavity and caused a frequency drift from the resonant frequency of the cavity. Power fluctuations of the cooling light led to atomic density variations in the cavity's central area, which increased the clock frequency instability through a cavity pulling effect. We overcame these limitations with appropriate solutions. A frequency stability of 3.5E-15 was achieved when the integrating time ? increased to 2E4 s.

physics.atom-ph↗

arXiv2016

Observation of magneto-optical rotation effects in cold $^{87}$Rb atoms in an integrating sphere

We present a modified scheme for detection of the magneto-optical rotation (MOR) effect, where a linearly polarized laser field is interacting with cold $^{87}$Rb atoms in an integrating sphere. The rotation angle of the probe beam's polarization plane is detected in the experiment. The results indicate that the biased magnetic field, the probe light intensity and detuning, and the cold atoms' temperature are key parameters for the MOR effect. This scheme may improve the contrast of the rotation signal and provide an useful approach for high contrast cold atom clocks and magnetometers.

physics.atom-ph↗

arXiv2015

A new scheme of compact cold atom clock based on diffuse laser cooling in a cylindrical cavity

We present a new scheme of compact Rubidium cold-atom clock which performs the diffuse light cooling, the microwave interrogation and the detection of the clock signal in a cylindrical microwave cavity. The diffuse light is produced by the reflection of the laser light at the inner surface of the microwave cavity. The pattern of injected laser beams is specially designed to make most of the cold atoms accumulate in the center of the microwave cavity. The microwave interrogation of cold atoms in the cavity leads to Ramsey fringes whose line-width is 24.5 Hz and the contrast of 95.6% when the free evolution time is 20 ms. The frequency stability of $7.3\times10^{-13}τ^{-1/2}$ has been achieved recently. The scheme of this physical package can largely reduce the complexity of the cold atom clock, and increase the performance of the clock.

physics.atom-ph↗