arXiv subjects

Yanxiang Gong

Publications and source records attributed to Yanxiang Gong.

10 recordsLinked to original sources

arXiv2024

Dynamical structures of misaligned circumbinary planets under hierarchical three-body systems

All circumbinary planets (CBPs) currently detected are located in almost co-planar configurations with respect to the binary orbit, due to the fact that CBPs with higher misalignment are more difficult to detect. However, observations of polar circumbinary gas and debris disks in recent years and long-term orbital stability of inclined planets indicate that it is possible to form misaligned CBPs around eccentricity binaries (even polar CBPs). In this work we focus on the dynamical structures of CBPs in a wide range of parameters in order to provide a guidance for the space where the binary can host planets for a long enough time. To this end, the dynamical model is approximated as a hierarchical three-body problem, and the secular approximation is formulated up to the hexadecapolar order in semimajor axis ratio. Dynamical maps show that there are complex structures in the parameter space. A web of secular resonances is produced in the entire parameter space and it can well explain those numerical structures arising in dynamical maps. Based on perturbative treatments, an adiabatic invariant is introduced and thus dynamical structures can be explored by analysing phase portraits. It is found that (a) the quadrupole-order resonance (nodal resonance) is responsible for the distribution of V-shape region, and high-order and secondary resonances dominate those structures inside or outside V-shape region, and (b) the secondary 1:1 resonance is the culprit causing symmetry breaking of dynamical structures inside polar region.

astro-ph.EP↗

arXiv2024

Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks

Mode collapse is a significant unsolved issue of generative adversarial networks. In this work, we examine the causes of mode collapse from a novel perspective. Due to the nonuniform sampling in the training process, some sub-distributions may be missed when sampling data. As a result, even when the generated distribution differs from the real one, the GAN objective can still achieve the minimum. To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution. When the generated distribution differs from the real one, GDF will make the objective harder to reach the minimal value, while the original global minimum is not changed. To deal with the circumstance when the overall real data is unreachable, we also propose a local distribution fitting (LDF) method. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.

cs.LG↗

arXiv2022

Unified Chinese License Plate Detection and Recognition with High Efficiency

Recently, deep learning-based methods have reached an excellent performance on License Plate (LP) detection and recognition tasks. However, it is still challenging to build a robust model for Chinese LPs since there are not enough large and representative datasets. In this work, we propose a new dataset named Chinese Road Plate Dataset (CRPD) that contains multi-objective Chinese LP images as a supplement to the existing public benchmarks. The images are mainly captured with electronic monitoring systems with detailed annotations. To our knowledge, CRPD is the largest public multi-objective Chinese LP dataset with annotations of vertices. With CRPD, a unified detection and recognition network with high efficiency is presented as the baseline. The network is end-to-end trainable with totally real-time inference efficiency (30 fps with 640p). The experiments on several public benchmarks demonstrate that our method has reached competitive performance. The code and dataset will be publicly available at https://github.com/yxgong0/CRPD.

cs.CV↗

arXiv2021

Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning

Previous feature alignment methods in Unsupervised domain adaptation(UDA) mostly only align global features without considering the mismatch between class-wise features. In this work, we propose a new coarse-to-fine feature alignment method using contrastive learning called CFContra. It draws class-wise features closer than coarse feature alignment or class-wise feature alignment only, therefore improves the model's performance to a great extent. We build it upon one of the most effective methods of UDA called entropy minimization to further improve performance. In particular, to prevent excessive memory occupation when applying contrastive loss in semantic segmentation, we devise a new way to build and update the memory bank. In this way, we make the algorithm more efficient and viable with limited memory. Extensive experiments show the effectiveness of our method and model trained on the GTA5 to Cityscapes dataset has boost mIOU by 3.5 compared to the MinEnt algorithm. Our code will be publicly available.

cs.CV↗

arXiv2020

What's the relationship between CNNs and communication systems?

The interpretability of Convolutional Neural Networks (CNNs) is an important topic in the field of computer vision. In recent years, works in this field generally adopt a mature model to reveal the internal mechanism of CNNs, helping to understand CNNs thoroughly. In this paper, we argue the working mechanism of CNNs can be revealed through a totally different interpretation, by comparing the communication systems and CNNs. This paper successfully obtained the corresponding relationship between the modules of the two, and verified the rationality of the corresponding relationship with experiments. Finally, through the analysis of some cutting-edge research on neural networks, we find the inherent relation between these two tasks can be of help in explaining these researches reasonably, as well as helping us discover the correct research direction of neural networks.

cs.CV↗

arXiv2019

STELA: A Real-Time Scene Text Detector with Learned Anchor

To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks. In this work, we present a simple and intuitive method for multi-oriented text detection where each location of feature maps only associates with one reference box. The idea is inspired from the twostage R-CNN framework that can estimate the location of objects with any shape by using learned proposals. The aim of our method is to integrate this mechanism into a onestage detector and employ the learned anchor which is obtained through a regression operation to replace the original one into the final predictions. Based on RetinaNet, our method achieves competitive performances on several public benchmarks with a totally real-time efficiency (26:5fps at 800p), which surpasses all of anchor-based scene text detectors. In addition, with less attention on anchor design, we believe our method is easy to be applied on other analogous detection tasks. The code will publicly available at https://github.com/xhzdeng/stela.

cs.CV↗

arXiv2019

Focus-Enhanced Scene Text Recognition with Deformable Convolutions

Recently, scene text recognition methods based on deep learning have sprung up in computer vision area. The existing methods achieved great performances, but the recognition of irregular text is still challenging due to the various shapes and distorted patterns. Consider that at the time of reading words in the real world, normally we will not rectify it in our mind but adjust our focus and visual fields. Similarly, through utilizing deformable convolutional layers whose geometric structures are adjustable, we present an enhanced recognition network without the steps of rectification to deal with irregular text in this work. A number of experiments have been applied, where the results on public benchmarks demonstrate the effectiveness of our proposed components and shows that our method has reached satisfactory performances. The code will be publicly available at https://github.com/Alpaca07/dtr soon.

cs.CV↗

arXiv2019

Detecting Multi-Oriented Text with Corner-based Region Proposals

Previous approaches for scene text detection usually rely on manually defined sliding windows. This work presents an intuitive two-stage region-based method to detect multi-oriented text without any prior knowledge regarding the textual shape. In the first stage, we estimate the possible locations of text instances by detecting and linking corners instead of shifting a set of default anchors. The quadrilateral proposals are geometry adaptive, which allows our method to cope with various text aspect ratios and orientations. In the second stage, we design a new pooling layer named Dual-RoI Pooling which embeds data augmentation inside the region-wise subnetwork for more robust classification and regression over these proposals. Experimental results on public benchmarks confirm that the proposed method is capable of achieving comparable performance with state-of-the-art methods. The code is publicly available at https://github.com/xhzdeng/crpn

cs.CV↗

arXiv2019

Generating Text Sequence Images for Recognition

Recently, methods based on deep learning have dominated the field of text recognition. With a large number of training data, most of them can achieve the state-of-the-art performances. However, it is hard to harvest and label sufficient text sequence images from the real scenes. To mitigate this issue, several methods to synthesize text sequence images were proposed, yet they usually need complicated preceding or follow-up steps. In this work, we present a method which is able to generate infinite training data without any auxiliary pre/post-process. We tackle the generation task as an image-to-image translation one and utilize conditional adversarial networks to produce realistic text sequence images in the light of the semantic ones. Some evaluation metrics are involved to assess our method and the results demonstrate that the caliber of the data is satisfactory. The code and dataset will be publicly available soon.

cs.CV↗

arXiv2005

Second Order Post Newtonian Equations of Light Propagation in Multiple Systems

The first order post Newtonian scheme in multiple systems presented by Damour-Soffel-Xu is extended to the second order one for light propagation without changing the advantage of the scheme on the linear partial differential equations of potential and vector potential. The spatial components of the metric tensor are extended to the second order level both in the global coordinates ($q_{ij}/c^4$ term) and in a local coordinates ($Q_{ab}/c^4$ term). The equations of $q_{ij}$ (or $Q_{ab}$) are deduced from Einstein field equations. The linear relationship between $q_{ij}$ and $Q_{ab}$ are presented also. The 2PN equations of light ray based on the extended scheme are deduced by means of the iterative method. We also use parametrized second post Newtonian metric tensor to substitute into the null geodetic equations to obtain the parametrized second order equations of light ray which might be useful in the observation and measurement in the future space missions.

gr-qc↗