arXiv subjects

Yu Liu

Publications and source records attributed to Yu Liu.

At least 937 records · Page 52Linked to original sources

arXiv2020

Modeling Event Propagation via Graph Biased Temporal Point Process

Temporal point process is widely used for sequential data modeling. In this paper, we focus on the problem of modeling sequential event propagation in graph, such as retweeting by social network users, news transmitting between websites, etc. Given a collection of event propagation sequences, conventional point process model consider only the event history, i.e. embed event history into a vector, not the latent graph structure. We propose a Graph Biased Temporal Point Process (GBTPP) leveraging the structural information from graph representation learning, where the direct influence between nodes and indirect influence from event history is modeled respectively. Moreover, the learned node embedding vector is also integrated into the embedded event history as side information. Experiments on a synthetic dataset and two real-world datasets show the efficacy of our model compared to conventional methods and state-of-the-art.

cs.SI↗

arXiv2020

A First Look at Commercial 5G Performance on Smartphones

We conduct to our knowledge a first measurement study of commercial 5G performance on smartphones by closely examining 5G networks of three carriers (two mmWave carriers, one mid-band carrier) in three U.S. cities. We conduct extensive field tests on 5G performance in diverse urban environments. We systematically analyze the handoff mechanisms in 5G and their impact on network performance. We explore the feasibility of using location and possibly other environmental information to predict the network performance. We also study the app performance (web browsing and HTTP download) over 5G. Our study consumes more than 15 TB of cellular data. Conducted when 5G just made its debut, it provides a "baseline" for studying how 5G performance evolves, and identifies key research directions on improving 5G users' experience in a cross-layer manner. We have released the data collected from our study (referred to as 5Gophers) at https://fivegophers.umn.edu/www20.

cs.NI↗

arXiv2020

A novel multimodal approach for hybrid brain-computer interface

Brain-computer interface (BCI) technologies have been widely used in many areas. In particular, non-invasive technologies such as electroencephalography (EEG) or near-infrared spectroscopy (NIRS) have been used to detect motor imagery, disease, or mental state. It has been already shown in literature that the hybrid of EEG and NIRS has better results than their respective individual signals. The fusion algorithm for EEG and NIRS sources is the key to implement them in real-life applications. In this research, we propose three fusion methods for the hybrid of the EEG and NIRS-based brain-computer interface system: linear fusion, tensor fusion, and $p$th-order polynomial fusion. Firstly, our results prove that the hybrid BCI system is more accurate, as expected. Secondly, the $p$th-order polynomial fusion has the best classification results out of the three methods, and also shows improvements compared with previous studies. For a motion imagery task and a mental arithmetic task, the best detection accuracy in previous papers were 74.20\% and 88.1\%, whereas our accuracy achieved was 77.53\% and 90.19\% . Furthermore, unlike complex artificial neural network methods, our proposed methods are not as computationally demanding.

cs.HC↗

arXiv2020

Cost-effectiveness Analysis of Antiepidemic Policies and Global Situation Assessment of COVID-19

With a two-layer contact-dispersion model and data in China, we analyze the cost-effectiveness of three types of antiepidemic measures for COVID-19: regular epidemiological control, local social interaction control, and inter-city travel restriction. We find that: 1) intercity travel restriction has minimal or even negative effect compared to the other two at the national level; 2) the time of reaching turning point is independent of the current number of cases, and only related to the enforcement stringency of epidemiological control and social interaction control measures; 3) strong enforcement at the early stage is the only opportunity to maximize both antiepidemic effectiveness and cost-effectiveness; 4) mediocre stringency of social interaction measures is the worst choice. Subsequently, we cluster countries/regions into four groups based on their control measures and provide situation assessment and policy suggestions for each group.

physics.soc-ph↗

arXiv2020

Change Detection in Heterogeneous Optical and SAR Remote Sensing Images via Deep Homogeneous Feature Fusion

Change detection in heterogeneous remote sensing images is crucial for disaster damage assessment. Recent methods use homogenous transformation, which transforms the heterogeneous optical and SAR remote sensing images into the same feature space, to achieve change detection. Such transformations mainly operate on the low-level feature space and may corrupt the semantic content, deteriorating the performance of change detection. To solve this problem, this paper presents a new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST). Unlike the existing methods, the DHFF method segregates the semantic content and the style features in the heterogeneous images to perform homogeneous transformation. The separation of the semantic content and the style in homogeneous transformation prevents the corruption of image semantic content, especially in the regions of change. In this way, the detection performance is improved with accurate homogeneous transformation. Furthermore, we present a new iterative IST (IIST) strategy, where the cost function in each IST iteration measures and thus maximizes the feature homogeneity in additional new feature subspaces for change detection. After that, change detection is accomplished accurately on the original and the transformed images that are in the same feature space. Real remote sensing images acquired by SAR and optical satellites are utilized to evaluate the performance of the proposed method. The experiments demonstrate that the proposed DHFF method achieves significant improvement for change detection in heterogeneous optical and SAR remote sensing images, in terms of both accuracy rate and Kappa index.

cs.CV↗

arXiv2020

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

As a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely. The basic idea is to enable anisotropic 3D receptive field by decomposing a 3D convolution into three consecutive 1D convolutions, and the kernel size for each such 1D convolution is adaptively determined on the fly. By stacking multiple such anisotropic convolution modules, the voxel-wise modeling capability can be further enhanced while maintaining a controllable amount of model parameters. Extensive experiments on two SSC benchmarks, NYU-Depth-v2 and NYUCAD, show the superior performance of the proposed method. Our code is available at https://waterljwant.github.io/SSC/

cs.CV↗

arXiv2020

DPGN: Distribution Propagation Graph Network for Few-shot Learning

Most graph-network-based meta-learning approaches model instance-level relation of examples. We extend this idea further to explicitly model the distribution-level relation of one example to all other examples in a 1-vs-N manner. We propose a novel approach named distribution propagation graph network (DPGN) for few-shot learning. It conveys both the distribution-level relations and instance-level relations in each few-shot learning task. To combine the distribution-level relations and instance-level relations for all examples, we construct a dual complete graph network which consists of a point graph and a distribution graph with each node standing for an example. Equipped with dual graph architecture, DPGN propagates label information from labeled examples to unlabeled examples within several update generations. In extensive experiments on few-shot learning benchmarks, DPGN outperforms state-of-the-art results by a large margin in 5% $\sim$ 12% under supervised setting and 7% $\sim$ 13% under semi-supervised setting. Code will be released.

cs.CV↗

arXiv2020

Spin-Triplet Excitonic Insulator: The Case of Graphone

While various excitonic insulators have been studied in the literature, due to the perceived too-small spin splitting, spin-triplet excitonic insulator is rare. In two-dimensional systems such as a graphone, however, it is possible, as revealed by first-principles calculations coupled with Bethe-Salpeter equation. The critical temperature, given by an effective Hamiltonian, is 11.5 K. While detecting excitonic insulators is still a daunting challenge, the condensation of triplet excitons will result in spin superfluidity, which can be directly measured by a transport experiment. Nonlocal dielectric screening also leads to an unexpected phenomenon, namely, an indirect-to-direct transition crossover between single-particle band and exciton dispersion in graphone, which offers yet another test by experiment.

cond-mat.mtrl-sci↗

arXiv2020

On the relation between relative rigid and support tilting

Let B be an extriangulated category with enough projectives and enough injectives. Let C be a fully rigid subcategory of B which admits a twin cotorsion pair ((C,K),(K,D)). The quotient category B/K is abelian, we assume that it is hereditary and has finite length. In this article, we study the relation between support tilting subcategories of B/K and maximal relative rigid subcategories of B. More precisely, we show that the image of any cluster tilting subcategory of B is support tilting in B/K and any support tilting subcategory in B/K can be lifted to a unique relative maximal rigid subcategory in B. We also give a bijection between these two classes of subcategories if C is generated by an object.

math.RT↗

arXiv2020

A statistical study of the plasma and composition distribution inside magnetic clouds: 1998-2011

A comprehensive analysis of plasma and composition characteristics inside magnetic clouds (MCs) observed by the Advanced Composition Explorer (ACE) spacecraft from 1998 February to 2011 August is presented. The results show that MCs have specific interior structures, and MCs of different speeds show differences in composition and structure. Compared with the slow MCs, fast MCs have enhanced mean charge states of iron, oxygen, silicon, magnesium, $\mathrm{O^{7+}/O^{6+}}$, $\mathrm{C^{6+}/C^{5+}}$, $\mathrm{C^{6+}/C^{4+}}$ and $\mathrm{Fe^{\geq16+}/Fe_{total}}$ values. For ionic species in fast MCs, a higher atomic number represents a greater enhancement of mean charge state than slow MCs. We also find that both the fast and slow MCs display bimodal structure distribution in the mean iron charge state ($\mathrm{\langle Q\rangle Fe}$), which suggests that the existence of flux rope prior to the eruption is common. Furthermore, the $\mathrm{\langle Q\rangle Fe} $, $\mathrm{Fe^{\geq16+}/Fe_{total}}$, and $\mathrm{O^{7+}/O^{6+}}$ ratio distribution inside fast MCs have the feature that the posterior peak is higher than the anterior one. This result agrees with the "standard model" for CME/flares, by which magnetic reconnection occurs beneath the flux rope, thereby ionizing the ions of the posterior part of flux rope sufficiently by high-energy electron collisions or by direct heating in the reconnection region.

astro-ph.SR↗

arXiv2020

Neutrino effects on the morphology of cosmic large-scale structure

In this work, we propose a powerful probe of neutrino effects on the large-scale structure (LSS) of the Universe, i.e., Minkowski functionals (MFs). The morphology of LSS can be fully described by four MFs. This tool, with strong statistical power, is robust to various systematics and can comprehensively probe all orders of N-point statistics. By using a pair of high-resolution N-body simulations, for the first time, we comprehensively studied the subtle neutrino effects on the morphology of LSS. For an ideal LSS survey of volume $\sim1.73$ Gpc$^3$/$h^3$, neutrino signals are mainly detected from void regions with a significant level up to $\thicksim 10σ$ and $\thicksim 300σ$ for CDM and total matter density fields, respectively. This demonstrates its enormous potential for much improving the neutrino mass constraint in the data analysis of up-coming ambitious LSS surveys.

astro-ph.CO↗

arXiv2020

Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images

Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods. The current generative models heavily rely on datasets with multi-view images of the same person. Thus, their generated results are restricted by the scale and domain of the data source. To overcome these challenges, we propose a novel unsupervised framework that can synthesize photo-realistic rotated faces using only single-view image collections in the wild. Our key insight is that rotating faces in the 3D space back and forth, and re-rendering them to the 2D plane can serve as a strong self-supervision. We leverage the recent advances in 3D face modeling and high-resolution GAN to constitute our building blocks. Since the 3D rotation-and-render on faces can be applied to arbitrary angles without losing details, our approach is extremely suitable for in-the-wild scenarios (i.e. no paired data are available), where existing methods fall short. Extensive experiments demonstrate that our approach has superior synthesis quality as well as identity preservation over the state-of-the-art methods, across a wide range of poses and domains. Furthermore, we validate that our rotate-and-render framework naturally can act as an effective data augmentation engine for boosting modern face recognition systems even on strong baseline models.

cs.CV↗

arXiv2020

Search to Distill: Pearls are Everywhere but not the Eyes

Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture. However, the knowledge of a neural network, which is represented by the network's output distribution conditioned on its input, depends not only on its parameters but also on its architecture. Hence, a more generalized approach for KD is to distill the teacher's knowledge into both the parameters and architecture of the student. To achieve this, we present a new Architecture-aware Knowledge Distillation (AKD) approach that finds student models (pearls for the teacher) that are best for distilling the given teacher model. In particular, we leverage Neural Architecture Search (NAS), equipped with our KD-guided reward, to search for the best student architectures for a given teacher. Experimental results show our proposed AKD consistently outperforms the conventional NAS plus KD approach, and achieves state-of-the-art results on the ImageNet classification task under various latency settings. Furthermore, the best AKD student architecture for the ImageNet classification task also transfers well to other tasks such as million level face recognition and ensemble learning.

cs.CV↗

arXiv2020

Revisiting the Sibling Head in Object Detector

The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years. This paper provides the observation that the spatial misalignment between the two object functions in the sibling head can considerably hurt the training process, but this misalignment can be resolved by a very simple operator called task-aware spatial disentanglement (TSD). Considering the classification and regression, TSD decouples them from the spatial dimension by generating two disentangled proposals for them, which are estimated by the shared proposal. This is inspired by the natural insight that for one instance, the features in some salient area may have rich information for classification while these around the boundary may be good at bounding box regression. Surprisingly, this simple design can boost all backbones and models on both MS COCO and Google OpenImage consistently by ~3% mAP. Further, we propose a progressive constraint to enlarge the performance margin between the disentangled and the shared proposals, and gain ~1% more mAP. We show the \algname{} breaks through the upper bound of nowadays single-model detector by a large margin (mAP 49.4 with ResNet-101, 51.2 with SENet154), and is the core model of our 1st place solution on the Google OpenImage Challenge 2019.

cs.CV↗

arXiv2020

KPNet: Towards Minimal Face Detector

The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors. In this work, we find that the appearance feature of a generic face is discriminative enough for a tiny and shallow neural network to verify from the background. And the essential barriers behind us are 1) the vague definition of the face bounding box and 2) tricky design of anchor-boxes or receptive field. Unlike most top-down methods for joint face detection and alignment, the proposed KPNet detects small facial keypoints instead of the whole face by in a bottom-up manner. It first predicts the facial landmarks from a low-resolution image via the well-designed fine-grained scale approximation and scale adaptive soft-argmax operator. Finally, the precise face bounding boxes, no matter how we define it, can be inferred from the keypoints. Without any complex head architecture or meticulous network designing, the KPNet achieves state-of-the-art accuracy on generic face detection and alignment benchmarks with only $\sim1M$ parameters, which runs at 1000fps on GPU and is easy to perform real-time on most modern front-end chips.

cs.CV↗

arXiv2020

1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation

This article introduces the solutions of the two champion teams, `MMfruit' for the detection track and `MMfruitSeg' for the segmentation track, in OpenImage Challenge 2019. It is commonly known that for an object detector, the shared feature at the end of the backbone is not appropriate for both classification and regression, which greatly limits the performance of both single stage detector and Faster RCNN \cite{ren2015faster} based detector. In this competition, we observe that even with a shared feature, different locations in one object has completely inconsistent performances for the two tasks. \textit{E.g. the features of salient locations are usually good for classification, while those around the object edge are good for regression.} Inspired by this, we propose the Decoupling Head (DH) to disentangle the object classification and regression via the self-learned optimal feature extraction, which leads to a great improvement. Furthermore, we adjust the soft-NMS algorithm to adj-NMS to obtain stable performance improvement. Finally, a well-designed ensemble strategy via voting the bounding box location and confidence is proposed. We will also introduce several training/inferencing strategies and a bag of tricks that give minor improvement. Given those masses of details, we train and aggregate 28 global models with various backbones, heads and 3+2 expert models, and achieves the 1st place on the OpenImage 2019 Object Detection Challenge on the both public and private leadboards. Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.

cs.CV↗

arXiv2020

Hearts of cotorsion pairs are functor categories over cohearts

We study hearts of cotorsion pairs in triangulated and exact categories.We give a sufficient and necessary condition when the hearts have enough projectives. We also show in such condition they are equivalent to functor categories over cohearts of the cotorsion pairs.

math.RT↗

arXiv2020

Top-1 Solution of Multi-Moments in Time Challenge 2019

In this technical report, we briefly introduce the solutions of our team 'Efficient' for the Multi-Moments in Time challenge in ICCV 2019. We first conduct several experiments with popular Image-Based action recognition methods TRN, TSN, and TSM. Then a novel temporal interlacing network is proposed towards fast and accurate recognition. Besides, the SlowFast network and its variants are explored. Finally, we ensemble all the above models and achieve 67.22\% on the validation set and 60.77\% on the test set, which ranks 1st on the final leaderboard. In addition, we release a new code repository for video understanding which unifies state-of-the-art 2D and 3D methods based on PyTorch. The solution of the challenge is also included in the repository, which is available at https://github.com/Sense-X/X-Temporal.

cs.CV↗