arXiv subjects

Xin Yang

Publications and source records attributed to Xin Yang.

At least 325 records · Page 18Linked to original sources

arXiv2022

CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative Panoptic-Regional Active Learning framework (CPRAL) to address the semantic segmentation task. For a small batch of images initially sampled with pixel-wise annotations, we employ panoptic information to initially select unlabeled samples. Considering the class imbalance in the segmentation dataset, we import a Regional Gaussian Attention module (RGA) to achieve semantics-biased selection. The subset is highlighted by vote entropy and then attended by Gaussian kernels to maximize the biased regions. We also propose a Contextual Labels Extension (CLE) to boost regional annotations with contextual attention guidance. With the collaboration of semantics-agnostic panoptic matching and regionbiased selection and extension, our CPRAL can strike a balance between labeling efforts and performance and compromise the semantics distribution. We perform extensive experiments on Cityscapes and BDD10K datasets and show that CPRAL outperforms the cutting-edge methods with impressive results and less labeling proportion.

cs.CV↗

arXiv2021

SECP-Net: SE-Connection Pyramid Network of Organ At Risk Segmentation for Nasopharyngeal Carcinoma

Nasopharyngeal carcinoma (NPC) is a kind of malignant tumor. Accurate and automatic segmentation of organs at risk (OAR) of computed tomography (CT) images is clinically significant. In recent years, deep learning models represented by U-Net have been widely applied in medical image segmentation tasks, which can help doctors with reduction of workload and get accurate results more quickly. In OAR segmentation of NPC, the sizes of OAR are variable, especially, some of them are small. Traditional deep neural networks underperform during segmentation due to the lack use of global and multi-size information. This paper proposes a new SE-Connection Pyramid Network (SECP-Net). SECP-Net extracts global and multi-size information flow with se connection (SEC) modules and a pyramid structure of network for improving the segmentation performance, especially that of small organs. SECP-Net also designs an auto-context cascaded network to further improve the segmentation performance. Comparative experiments are conducted between SECP-Net and other recently methods on a dataset with CT images of head and neck. Five-fold cross validation is used to evaluate the performance based on two metrics, i.e., Dice and Jaccard similarity. Experimental results show that SECP-Net can achieve SOTA performance in this challenging task.

eess.IV↗

arXiv2021

Lower Regularity Solutions of the Non-homogeneous Boundary-Value Problem for a Higher Order Boussinesq Equation in a Quarter Plane

We continue to study the initial-boundary-value problem of the sixth order Boussinesq equation in a quarter plane with non-homogeneous boundary conditions: \begin{equation*} \begin{cases} u_{tt}-u_{xx}+βu_{xxxx}-u_{xxxxxx}+(u^2)_{xx}=0,\quad x,t\in \mathbb{R}^+,\\ u(x,0)=φ(x), u_t(x,0)=ψ''(x), \\ u(0,t)=h_1(t), u_{xx}(0,t)=h_2(t), u_{xxxx}(0,t)=h_3(t), \end{cases} \end{equation*} where $β=\pm1$. We show that the problem is locally analytically well-posed in the space $H^s(\mathbb{R}^+)$ for any $ s> -\frac34 $ with the initial-value data $$(φ,ψ)\in H^s(\mathbb{R}^+)\times H^{s-1}(\mathbb{R}^+)$$ and the boundary-value data $$(h_1,h_2,h_3) \in H^{\frac{s+1}{3}}(\mathbb{R}^+)\times H^{\frac{s-1}{3}}(\mathbb{R}^+)\times H^{\frac{s-3}{3}}(\mathbb{R}^+).$$

math.AP↗

arXiv2021

Learning to Detect Instance-level Salient Objects Using Complementary Image Labels

Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.

cs.CV↗

arXiv2021

Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network

Automated methods for detecting pulmonary embolisms (PEs) on CT pulmonary angiography (CTPA) images are of high demand. Existing methods typically employ separate steps for PE candidate detection and false positive removal, without considering the ability of the other step. As a result, most existing methods usually suffer from a high false positive rate in order to achieve an acceptable sensitivity. This study presents an end-to-end trainable convolutional neural network (CNN) where the two steps are optimized jointly. The proposed CNN consists of three concatenated subnets: 1) a novel 3D candidate proposal network for detecting cubes containing suspected PEs, 2) a 3D spatial transformation subnet for generating fixed-sized vessel-aligned image representation for candidates, and 3) a 2D classification network which takes the three cross-sections of the transformed cubes as input and eliminates false positives. We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78.9%, 80.7% and 80.7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods. We have further evaluated our system on our own dataset consisting of 129 CTPA data with a total of 269 emboli. Our system achieves a sensitivity of 63.2%, 78.9% and 86.8% at 2 false positives per volume at 0mm, 2mm and 5mm localization error.

cs.CV↗

arXiv2021

High-Tc superconductivity in clathrate calcium hydride CaH6

Recent discovery of superconductive rare earth/actinide superhydrides has ushered in a new era of superconductivity research at high pressures. This distinct type of clathrate metal hydrides was first proposed for alkaline-earth-metal hydride CaH6 that, however, has long eluded experimental synthesis, impeding an understanding of pertinent physics. Here, we report successful synthesis of CaH6 and its measured superconducting critical temperature Tc of 215 K at 172 GPa, which is evidenced by a sharp drop of resistivity to zero and a characteristic decrease of Tc under a magnetic field up to 9 T.An estimate based on the Werthamer-Helfand-Hohenberg model gives a giant zero-temperature upper critical magnetic field of 203 T. These remarkable benchmark superconducting properties place CaH6 among the most outstanding high-Tc superhydrides, marking it as the hitherto only clathrate metal hydride outside the family of rare earth/actinide hydrides. This exceptional case raises great prospects of expanding the extraordinary class of high-Tc superhydrides to a broader variety of compounds that possess more diverse material features and physics characteristics.

cond-mat.supr-con↗

arXiv2021

Scaling of variations in traveling distances and times of taxi routes

The importance of understanding human mobility patterns has led many studies to examine their spatial-temporal scaling laws. These studies mainly reveal that human travel can be highly non-homogeneous with power-law scaling distributions of distances and times. However, investigating and quantifying the extent of variability in time and space when traveling the same air distance has not been addressed so far. Using taxi data from five large cities, we focus on several novel measures of distance and time to explore the spatio-temporal variations of taxi travel routes relative to their typical routes during peak and nonpeak periods. To compare all trips using a single measure, we calculate the distributions of the ratios between actual travel distances and the average travel distance as well as between actual travel times and the average travel time for all origin destinations (OD) during peak and nonpeak periods. In this way, we measure the scaling of the distribution of all single trip paths with respect to their mean trip path. Our results surprisingly demonstrate very broad distributions for both the distance ratio and time ratio, characterized by a long-tail power-law distribution. Moreover, all analyzed cities have larger exponents in peak hours than in nonpeak hours. We suggest that the interesting results of shorter trip lengths and times, characterized by larger exponents during rush hours, are due to the higher availability of travelers in rush hours compared to non-rush hours...

physics.soc-ph↗

arXiv2021

Monocular Depth Estimation with Sharp Boundary

Monocular depth estimation is the base task in computer vision. It has a tremendous development in the decade with the development of deep learning. But the boundary blur of the depth map is still a serious problem. Research finds the boundary blur problem is mainly caused by two factors, first, the low-level features containing boundary and structure information may loss in deeper networks during the convolution process., second, the model ignores the errors introduced by the boundary area due to the few portions of the boundary in the whole areas during the backpropagation. In order to mitigate the boundary blur problem, we focus on the above two impact factors. Firstly, we design a scene understanding module to learn the global information with low- and high-level features, and then to transform the global information to different scales with our proposed scale transform module according to the different phases in the decoder. Secondly, we propose a boundary-aware depth loss function to pay attention to the effects of the boundary's depth value. The extensive experiments show that our method can predict the depth maps with clearer boundaries, and the performance of the depth accuracy base on NYU-depth v2 and SUN RGB-D is competitive.

cs.CV↗

arXiv2021

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking

Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking. This paper focuses on effectively representing and utilizing complementary features from the frame domain and event domain for boosting object tracking performance in challenge scenarios. Specifically, we propose Common Features Extractor (CFE) to learn potential common representations from the RGB domain and event domain. For learning the unique features of the two domains, we utilize a Unique Extractor for Event (UEE) based on Spiking Neural Networks to extract edge cues in the event domain which may be missed in RGB in some challenging conditions, and a Unique Extractor for RGB (UER) based on Deep Convolutional Neural Networks to extract texture and semantic information in RGB domain. Extensive experiments on standard RGB benchmark and real event tracking dataset demonstrate the effectiveness of the proposed approach. We show our approach outperforms all compared state-of-the-art tracking algorithms and verify event-based data is a powerful cue for tracking in challenging scenes.

cs.CV↗

arXiv2021

Smooth solutions to the heat equation which are nowhere analytic in time

The existence of smooth but nowhere analytic functions is well-known (du Bois-Reymond, Math. Ann., 21(1):109-117, 1883). However, smooth solutions to the heat equation are usually analytic in the space variable. It is also well-known (Kowalevsky, Crelle, 80:1-32, 1875) that a solution to the heat equation may not be time-analytic at $t=0$ even if the initial function is real analytic. Recently, it was shown in \cite{Zha20, DZ20, DP20} that solutions to the heat equation in the whole space, or half space with zero boundary value, are analytic in time under essentially optimal conditions. In this paper, we show that time analyticity is not always true in domains with general boundary conditions or without suitable growth conditions. More precisely, we construct two bounded solutions to the heat equation in the half plane which are nowhere analytic in time. In addition, for any $δ>0$, we find a solution to the heat equation on the whole plane, with exponential growth of order $2+δ$, which is nowhere analytic in time.

math.AP↗

arXiv2021

Runtime Interchange for Adaptive Re-use of Intelligent Cyber-Physical System Controllers

Cyber-Physical Systems (CPSs) such as those found within autonomous vehicles are increasingly adopting Artificial Neural Network (ANN)-based controllers. To ensure the safety of these controllers, there is a spate of recent activity to formally verify the ANN-based designs. There are two challenges with these approaches: (1) The verification of such systems is difficult and time consuming. (2) These verified controllers are not able to adapt to frequent requirements changes, which are typical in situations like autonomous driving. This raises the question: how can trained and verified controllers, which have gone through expensive training and verification processes, be re-used to deal with requirement changes? This paper addresses this challenge for the first time by proposing a new framework that is capable of dealing with requirement changes at runtime through a mechanism we term runtime interchange. Our approach functions via a continual exchange and selection process of multiple pre-verified controllers. It represents a key step on the way to component-oriented engineering for intelligent designs, as it preserves the behaviours of the original controllers while introducing additional functionality. To demonstrate the efficacy of our approach we utilise an existing autonomous driving case study as well as a set of smaller benchmarks. These show that introduced overheads are extremely minimal and that the approach is very scalable.

cs.SE↗

arXiv2021

Object Tracking by Jointly Exploiting Frame and Event Domain

Inspired by the complementarity between conventional frame-based and bio-inspired event-based cameras, we propose a multi-modal based approach to fuse visual cues from the frame- and event-domain to enhance the single object tracking performance, especially in degraded conditions (e.g., scenes with high dynamic range, low light, and fast-motion objects). The proposed approach can effectively and adaptively combine meaningful information from both domains. Our approach's effectiveness is enforced by a novel designed cross-domain attention schemes, which can effectively enhance features based on self- and cross-domain attention schemes; The adaptiveness is guarded by a specially designed weighting scheme, which can adaptively balance the contribution of the two domains. To exploit event-based visual cues in single-object tracking, we construct a large-scale frame-event-based dataset, which we subsequently employ to train a novel frame-event fusion based model. Extensive experiments show that the proposed approach outperforms state-of-the-art frame-based tracking methods by at least 10.4% and 11.9% in terms of representative success rate and precision rate, respectively. Besides, the effectiveness of each key component of our approach is evidenced by our thorough ablation study.

cs.CV↗

arXiv2021

Self-supervised Representation Learning for Trip Recommendation

Trip recommendation is a significant and engaging location-based service that can help new tourists make more customized travel plans. It often attempts to suggest a sequence of point of interests (POIs) for a user who requests a personalized travel demand. Conventional methods either leverage the heuristic algorithms (e.g., dynamic programming) or statistical analysis (e.g., Markov models) to search or rank a POI sequence. These procedures may fail to capture the diversity of human needs and transitional regularities. They even provide recommendations that deviate from tourists' real travel intention when the trip data is sparse. Although recent deep recursive models (e.g., RNN) are capable of alleviating these concerns, existing solutions hardly recognize the practical reality, such as the diversity of tourist demands, uncertainties in the trip generation, and the complex visiting preference. Inspired by the advance in deep learning, we introduce a novel self-supervised representation learning framework for trip recommendation -- SelfTrip, aiming at tackling the aforementioned challenges. Specifically, we propose a two-step contrastive learning mechanism concerning the POI representation, as well as trip representation. Furthermore, we present four trip augmentation methods to capture the visiting uncertainties in trip planning. We evaluate our SelfTrip on four real-world datasets, and extensive results demonstrate the promising gain compared with several cutting-edge benchmarks, e.g., up to 4% and 12% on F1 and pair-F1, respectively.

cs.IR↗

arXiv2021

Design and Synthesis of Clathrate LaB8 with Superconductivity

Boron-based clathrate materials, typically with three-dimensional networks of B atoms, have tunable properties through substitution of guest atoms, but the tuning of B cages themselves has not yet been developed. By combining crystal structural search with the laser-heated diamond anvil cell technique, we successfully synthesized a new B-based clathrate boride, LaB8, at ~108 GPa and ~2100 K. The novel structure has a B-richest cage, with 26 B atoms encapsulating a single La atom. LaB8 demonstrates phonon-mediated superconductivity with an estimated transition temperature of 14 K at ambient pressure, mainly originating from electron-phonon coupling of B cage. This work creates a prototype platform for subsequent investigation on tunable electronic properties through the choice of captured atoms.

cond-mat.mtrl-sci↗

arXiv2021

En route to high Tc superconductivity via Rb substitution of guest metal atoms in SrB3C3 clathrate

Recently, a host/guest clathrate SrB3C3 with sp3-bonded boron-carbon framework was synthesized at around 50 GPa. On the basis of electron count, the structure is understood as guest Sr2+ cations intercalated in the (B3C3)3- framework. Previous calculations suggest that SrB3C3 is a hole conductor with an estimated superconducting critical temperature (Tc) of 42 K at ambient pressure. If atoms with similar radius, such as Rb, can substitute Sr2+ in the lattice, the electronic as well as superconductivity properties of this material will be modified significantly. Here, we perform extensive simulations on the stability and physical properties of Rb-Sr-B3C3 system using first-principles density functional calculation in combination with cluster expansion and CALYPSO structure prediction method. We predict a phonon-mediated superconductor Rb0.5Sr0.5B3C3 with a remarkably high Tc of 78 K at ambient pressure, which is a significant improvement from the estimated value (42 K) in SrB3C3. The current results suggest that substitution of alkali atom in synthesized clathrate SrB3C3 is a viable route toward high-Tc compounds.

cond-mat.mtrl-sci↗

arXiv2021

A Vision-based Irregular Obstacle Avoidance Framework via Deep Reinforcement Learning

Deep reinforcement learning has achieved great success in laser-based collision avoidance work because the laser can sense accurate depth information without too much redundant data, which can maintain the robustness of the algorithm when it is migrated from the simulation environment to the real world. However, high-cost laser devices are not only difficult to apply on a large scale but also have poor robustness to irregular objects, e.g., tables, chairs, shelves, etc. In this paper, we propose a vision-based collision avoidance framework to solve the challenging problem. Our method attempts to estimate the depth and incorporate the semantic information from RGB data to obtain a new form of data, pseudo-laser data, which combines the advantages of visual information and laser information. Compared to traditional laser data that only contains the one-dimensional distance information captured at a certain height, our proposed pseudo-laser data encodes the depth information and semantic information within the image, which makes our method more effective for irregular obstacles. Besides, we adaptively add noise to the laser data during the training stage to increase the robustness of our model in the real world, due to the estimated depth information is not accurate. Experimental results show that our framework achieves state-of-the-art performance in several unseen virtual and real-world scenarios.

cs.RO↗

arXiv2021

Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction

3D ultrasound (US) is widely used for its rich diagnostic information. However, it is criticized for its limited field of view. 3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan. The existing deep learning based methods only focus on the basic cases of skill sequences, and the model relies on the training data heavily. The sequences in real clinical practice are a mix of diverse skills and have complex scanning paths. Besides, deep models should adapt themselves to the testing cases with prior knowledge for better robustness, rather than only fit to the training cases. In this paper, we propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences. Our contribution is three-fold. First, we advance a novel online learning framework by designing a differentiable reconstruction algorithm. It realizes an end-to-end optimization from section sequences to the reconstructed volume. Second, a self-supervised learning method is developed to explore the context information that reconstructed by the testing data itself, promoting the perception of the model. Third, inspired by the effectiveness of shape prior, we also introduce adversarial training to strengthen the learning of anatomical shape prior in the reconstructed volume. By mining the context and structural cues of the testing data, our online learning methods can drive the model to handle complex skill sequences. Experimental results on developmental dysplasia of the hip US and fetal US datasets show that, our proposed method can outperform the start-of-the-art methods regarding the shift errors and path similarities.

cs.CV↗

arXiv2021

WRICNet:A Weighted Rich-scale Inception Coder Network for Multi-Resolution Remote Sensing Image Change Detection

Majority models of remote sensing image changing detection can only get great effect in a specific resolution data set. With the purpose of improving change detection effectiveness of the model in the multi-resolution data set, a weighted rich-scale inception coder network (WRICNet) is proposed in this article, which can make a great fusion of shallow multi-scale features, and deep multi-scale features. The weighted rich-scale inception module of the proposed can obtain shallow multi-scale features, the weighted rich-scale coder module can obtain deep multi-scale features. The weighted scale block assigns appropriate weights to features of different scales, which can strengthen expressive ability of the edge of the changing area. The performance experiments on the multi-resolution data set demonstrate that, compared to the comparative methods, the proposed can further reduce the false alarm outside the change area, and the missed alarm in the change area, besides, the edge of the change area is more accurate. The ablation study of the proposed shows that the training strategy, and improvements of this article can improve the effectiveness of change detection.

cs.CV↗