arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 955 records · Page 53Linked to original sources

arXiv2019

SUBARU Near-Infrared Imaging Polarimetry of Misaligned Disks Around The SR24 Hierarchical Triple System

The SR24 multi-star system hosts both circumprimary and circumsecondary disks, which are strongly misaligned from each other. The circumsecondary disk is circumbinary in nature. Interestingly, both disks are interacting, and they possibly rotate in opposite directions. To investigate the nature of this unique twin disk system, we present 0.''1 resolution near-infrared polarized intensity images of the circumstellar structures around SR24, obtained with HiCIAO mounted on the Subaru 8.2 m telescope. Both the circumprimary disk and the circumsecondary disk are resolved and have elongated features. While the position angle of the major axis and radius of the NIR polarization disk around SR24S are 55$^{\circ}$ and 137 au, respectively, those around SR24N are 110$^{\circ}$ and 34 au, respectively. With regard to overall morphology, the circumprimary disk around SR24S shows strong asymmetry, whereas the circumsecondary disk around SR24N shows relatively strong symmetry. Our NIR observations confirm the previous claim that the circumprimary and circumsecondary disks are misaligned from each other. Both the circumprimary and circumsecondary disks show similar structures in $^{12}$CO observations in terms of its size and elongation direction. This consistency is because both NIR and $^{12}$CO are tracing surface layers of the flared disks. As the radius of the polarization disk around SR24N is roughly consistent with the size of the outer Roche lobe, it is natural to interpret the polarization disk around SR24N as a circumbinary disk surrounding the SR24Nb-Nc system.

astro-ph.SR↗

arXiv2019

PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing

In this paper, we introduce a Point Recurrent Neural Network (PointRNN) for moving point cloud processing. At each time step, PointRNN takes point coordinates $\boldsymbol{P} \in \mathbb{R}^{n \times 3}$ and point features $\boldsymbol{X} \in \mathbb{R}^{n \times d}$ as input ($n$ and $d$ denote the number of points and the number of feature channels, respectively). The state of PointRNN is composed of point coordinates $\boldsymbol{P}$ and point states $\boldsymbol{S} \in \mathbb{R}^{n \times d'}$ ($d'$ denotes the number of state channels). Similarly, the output of PointRNN is composed of $\boldsymbol{P}$ and new point features $\boldsymbol{Y} \in \mathbb{R}^{n \times d''}$ ($d''$ denotes the number of new feature channels). Since point clouds are orderless, point features and states from two time steps can not be directly operated. Therefore, a point-based spatiotemporally-local correlation is adopted to aggregate point features and states according to point coordinates. We further propose two variants of PointRNN, i.e., Point Gated Recurrent Unit (PointGRU) and Point Long Short-Term Memory (PointLSTM). We apply PointRNN, PointGRU and PointLSTM to moving point cloud prediction, which aims to predict the future trajectories of points in a set given their history movements. Experimental results show that PointRNN, PointGRU and PointLSTM are able to produce correct predictions on both synthetic and real-world datasets, demonstrating their ability to model point cloud sequences. The code has been released at \url{https://github.com/hehefan/PointRNN}.

cs.CV↗

arXiv2019

Tweedie Gradient Boosting for Extremely Unbalanced Zero-inflated Data

Tweedie's compound Poisson model is a popular method to model insurance claims with probability mass at zero and nonnegative, highly right-skewed distribution. In particular, it is not uncommon to have extremely unbalanced data with excessively large proportion of zero claims, and even traditional Tweedie model may not be satisfactory for fitting the data. In this paper, we propose a boosting-assisted zero-inflated Tweedie model, called EMTboost, that allows zero probability mass to exceed a traditional model. We makes a nonparametric assumption on its Tweedie model component, that unlike a linear model, is able to capture nonlinearities, discontinuities, and complex higher order interactions among predictors. A specialized Expectation-Maximization algorithm is developed that integrates a blockwise coordinate descent strategy and a gradient tree-boosting algorithm to estimate key model parameters. We use extensive simulation and data analysis on synthetic zero-inflated auto-insurance claim data to illustrate our method's prediction performance.

stat.CO↗

arXiv2019

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks

Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pruning algorithm is a three-stage pipeline, i.e., training, pruning, and retraining. Prevailing approaches fix the pruned filters to zero during retraining, and thus significantly reduce the optimization space. Besides, they directly prune a large number of filters at first, which would cause unrecoverable information loss. To solve these problems, we propose an Asymptotic Soft Filter Pruning (ASFP) method to accelerate the inference procedure of the deep neural networks. First, we update the pruned filters during the retraining stage. As a result, the optimization space of the pruned model would not be reduced but be the same as that of the original model. In this way, the model has enough capacity to learn from the training data. Second, we prune the network asymptotically. We prune few filters at first and asymptotically prune more filters during the training procedure. With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable. Experiments show the effectiveness of our ASFP on image classification benchmarks. Notably, on ILSVRC-2012, our ASFP reduces more than 40% FLOPs on ResNet-50 with only 0.14% top-5 accuracy degradation, which is higher than the soft filter pruning (SFP) by 8%.

cs.CV↗

arXiv2019

Self-Correction for Human Parsing

Labeling pixel-level masks for fine-grained semantic segmentation tasks, e.g. human parsing, remains a challenging task. The ambiguous boundary between different semantic parts and those categories with similar appearance usually are confusing, leading to unexpected noises in ground truth masks. To tackle the problem of learning with label noises, this work introduces a purification strategy, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models. In particular, starting from a model trained with inaccurate annotations as initialization, we design a cyclically learning scheduler to infer more reliable pseudo-masks by iteratively aggregating the current learned model with the former optimal one in an online manner. Besides, those correspondingly corrected labels can in turn to further boost the model performance. In this way, the models and the labels will reciprocally become more robust and accurate during the self-correction learning cycles. Benefiting from the superiority of SCHP, we achieve the best performance on two popular single-person human parsing benchmarks, including LIP and Pascal-Person-Part datasets. Our overall system ranks 1st in CVPR2019 LIP Challenge. Code is available at https://github.com/PeikeLi/Self-Correction-Human-Parsing.

cs.CV↗

arXiv2019

Network Pruning via Transformable Architecture Search

Network pruning reduces the computation costs of an over-parameterized network without performance damage. Prevailing pruning algorithms pre-define the width and depth of the pruned networks, and then transfer parameters from the unpruned network to pruned networks. To break the structure limitation of the pruned networks, we propose to apply neural architecture search to search directly for a network with flexible channel and layer sizes. The number of the channels/layers is learned by minimizing the loss of the pruned networks. The feature map of the pruned network is an aggregation of K feature map fragments (generated by K networks of different sizes), which are sampled based on the probability distribution.The loss can be back-propagated not only to the network weights, but also to the parameterized distribution to explicitly tune the size of the channels/layers. Specifically, we apply channel-wise interpolation to keep the feature map with different channel sizes aligned in the aggregation procedure. The maximum probability for the size in each distribution serves as the width and depth of the pruned network, whose parameters are learned by knowledge transfer, e.g., knowledge distillation, from the original networks. Experiments on CIFAR-10, CIFAR-100 and ImageNet demonstrate the effectiveness of our new perspective of network pruning compared to traditional network pruning algorithms. Various searching and knowledge transfer approaches are conducted to show the effectiveness of the two components. Code is at: https://github.com/D-X-Y/NAS-Projects.

cs.CV↗

arXiv2019

Searching for A Robust Neural Architecture in Four GPU Hours

Conventional neural architecture search (NAS) approaches are based on reinforcement learning or evolutionary strategy, which take more than 3000 GPU hours to find a good model on CIFAR-10. We propose an efficient NAS approach learning to search by gradient descent. Our approach represents the search space as a directed acyclic graph (DAG). This DAG contains billions of sub-graphs, each of which indicates a kind of neural architecture. To avoid traversing all the possibilities of the sub-graphs, we develop a differentiable sampler over the DAG. This sampler is learnable and optimized by the validation loss after training the sampled architecture. In this way, our approach can be trained in an end-to-end fashion by gradient descent, named Gradient-based search using Differentiable Architecture Sampler (GDAS). In experiments, we can finish one searching procedure in four GPU hours on CIFAR-10, and the discovered model obtains a test error of 2.82\% with only 2.5M parameters, which is on par with the state-of-the-art. Code is publicly available on GitHub: https://github.com/D-X-Y/NAS-Projects.

cs.CV↗

arXiv2019

Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization

Localizing objects with weak supervision in an image is a key problem of the research in computer vision community. Many existing Weakly-Supervised Object Localization (WSOL) approaches tackle this problem by estimating the most discriminative regions with feature maps (activation maps) obtained by Deep Convolutional Neural Network, that is, only the objects or parts of them with the most discriminative response will be located. However, the activation maps often display different local maximum responses or relatively weak response when one image contains multiple objects with the same type or small objects. In this paper, we propose a simple yet effective multi-scale discriminative region discovery method to localize not only more integral objects but also as many as possible with only image-level class labels. The gradient weights flowing into different convolutional layers of CNN are taken as the input of our method, which is different from previous methods only considering that of the final convolutional layer. To mine more discriminative regions for the task of object localization, the multiple local maximum from the gradient weight maps are leveraged to generate the localization map with a parallel sliding window. Furthermore, multi-scale localization maps from different convolutional layers are fused to produce the final result. We evaluate the proposed method with the foundation of VGGnet on the ILSVRC 2016, CUB-200-2011 and PASCAL VOC 2012 datasets. On ILSVRC 2016, the proposed method yields the Top-1 localization error of 48.65\%, which outperforms previous results by 2.75\%. On PASCAL VOC 2012, our approach achieve the highest localization accuracy of 0.43. Even for CUB-200-2011 dataset, our method still achieves competitive results.

cs.CV↗

arXiv2019

FASTER Recurrent Networks for Efficient Video Classification

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10x? while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.

cs.CV↗

arXiv2019

Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification

Prevailing deep convolutional neural networks (CNNs) for person re-IDentification (reID) are usually built upon ResNet or VGG backbones, which were originally designed for classification. Because reID is different from classification, the architecture should be modified accordingly. We propose to automatically search for a CNN architecture that is specifically suitable for the reID task. There are three aspects to be tackled. First, body structural information plays an important role in reID but it is not encoded in backbones. Second, Neural Architecture Search (NAS) automates the process of architecture design without human effort, but no existing NAS methods incorporate the structure information of input images. Third, reID is essentially a retrieval task but current NAS algorithms are merely designed for classification. To solve these problems, we propose a retrieval-based search algorithm over a specifically designed reID search space, named Auto-ReID. Our Auto-ReID enables the automated approach to find an efficient and effective CNN architecture for reID. Extensive experiments demonstrate that the searched architecture achieves state-of-the-art performance while reducing 50% parameters and 53% FLOPs compared to others.

cs.CV↗

arXiv2019

Linear spectropolarimetry of 35 Type Ia Supernovae with VLT/FORS: An analysis of the Si II line polarization

Spectropolarimetry enables us to measure the geometry and chemical structure of the ejecta in supernova explosions, which is fundamental for the understanding of their explosion mechanism(s) and progenitor systems. We collected archival data of 35 Type Ia Supernovae (SNe Ia), observed with FORS on the Very Large Telescope at 127 epochs in total. We examined the polarization of the Si II $λ$6355 $Å$ line (p$_{\rm Si II}$) as a function of time which is seen to peak at a range of various polarization degrees and epochs relative to maximum brightness. We reproduced the $Δ$m$_{15}$-p$_{\rm Si II}$ relationship identified in a previous study, and show that subluminous and transitional objects display polarization values below the $Δ$m$_{15}$-p$_{\rm Si II}$ relationship for normal SNe Ia. We found a statistically significant linear relationship between the polarization of the Si II $λ$6355 $Å$ line before maximum brightness and the Si II line velocity and suggest that this, along with the $Δ$m$_{15}$-p$_{\rm Si II}$ relationship, may be explained in the context of a delayed-detonation model. In contrast, we compared our observations to numerical predictions in the $Δ$m$_{15}$-v$_{\rm Si II}$ plane and found a dichotomy in the polarization properties between Chandrasekhar and sub-Chandrasekhar mass explosions, which supports the possibility of two distinct explosion mechanisms. A subsample of SNe display evolution of loops in the $q$-$u$ plane that suggests a more complex Si structure with depth. This insight, which could not be gleaned from total flux spectra, presents a new constraint on explosion models. Finally, we compared our statistical sample of the Si II polarization to quantitative predictions of the polarization levels for the double-detonation, delayed-detonation, and violent-merger models.

astro-ph.HE↗

arXiv2019

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

Facial landmark detection aims to localize the anatomically defined points of human faces. In this paper, we study facial landmark detection from partially labeled facial images. A typical approach is to (1) train a detector on the labeled images; (2) generate new training samples using this detector's prediction as pseudo labels of unlabeled images; (3) retrain the detector on the labeled samples and partial pseudo labeled samples. In this way, the detector can learn from both labeled and unlabeled data to become robust. In this paper, we propose an interaction mechanism between a teacher and two students to generate more reliable pseudo labels for unlabeled data, which are beneficial to semi-supervised facial landmark detection. Specifically, the two students are instantiated as dual detectors. The teacher learns to judge the quality of the pseudo labels generated by the students and filter out unqualified samples before the retraining stage. In this way, the student detectors get feedback from their teacher and are retrained by premium data generated by itself. Since the two students are trained by different samples, a combination of their predictions will be more robust as the final prediction compared to either prediction. Extensive experiments on 300-W and AFLW benchmarks show that the interactions between teacher and students contribute to better utilization of the unlabeled data and achieves state-of-the-art performance.

cs.CV↗

arXiv2019

Recognizing Part Attributes with Insufficient Data

Recognizing attributes of objects and their parts is important to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications. Furthermore, most existing part attribute recognition methods rely on the part annotation which is more expensive to obtain. To solve the data insufficiency problem and get rid of dependence on the part annotation, we introduce a novel Concept Sharing Network (CSN) for part attribute recognition. A great advantage of CSN is its capability of recognizing the part attribute (a combination of part location and appearance pattern) that has insufficient or zero training data, by learning the part location and appearance pattern respectively from the training data that usually mix them in a single label. Extensive experiments on CUB-200-2011 [51], CelebA [35] and a newly proposed human attribute dataset demonstrate the effectiveness of CSN and its advantages over other methods, especially for the attributes with few training samples. Further experiments show that CSN can also perform zero-shot part attribute recognition. The code will be made available at https://github.com/Zhaoxiangyun/Concept-Sharing-Network.

cs.CV↗

arXiv2019

Overview on High energy String Scattering Amplitudes and Symmetries of String Theory

We overview symmetries of string scattering amplitudes in the high energy limits of both the fixed angle or Gross regime (GR) and the fixed momentum transfer or Regge regime (RR). We calculated high energy string scattering amplitudes (SSA) at arbitrary mass levels for both regimes. We discovered the infinite linear relations among fixed angle string amplitudes and the infinite recurrence relations among Regge string amplitudes. The linear relations we obtained in the GR corrected the saddle point calculations by Gross, Gross and Mende. In addition, for the high energy closed string scatterings, our results differ from theirs by an oscillating prefactor which was crucial to recover the KLT relation valid for all energies. We showed that all the high energy string amplitudes can be solved by the linear or recurrence relations so that all the string amplitudes can be expressed in terms of a single string amplitude. We further found that, at each mass level, the ratios among the fixed angle amplitudes can be extracted from the Regge string scattering amplitudes. Finally, we review the recent developments on the discovery of infinite number of recurrence relations valid for all energies among Lauricella SSA. The symmetries or relations among SSA at various limits obtained previously can be exactly reproduced. It leads us to argue that the known SL(K+3,C) dynamical symmetry of the Lauricella function maybe crucial to probe spacetime symmetry of string theory.

hep-th↗

arXiv2019

Attract or Distract: Exploit the Margin of Open Set

Open set domain adaptation aims to diminish the domain shift across domains, with partially shared classes. There exist unknown target samples out of the knowledge of source domain. Compared to the close set setting, how to separate the unknown (unshared) class from the known (shared) ones plays a key role. Whereas, previous methods did not emphasize the semantic structure of the open set data, which may introduce bias into the domain alignment and confuse the classifier around the decision boundary. In this paper, we exploit the semantic structure of open set data from two aspects: 1) Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source. 2)Semantic Contrastive Mapping, which aims to push the unknown class away from the decision boundary. Empirically, we demonstrate that our method performs favourably against the state-of-the-art methods on representative benchmarks, e.g. Digit datasets and Office-31 datasets.

cs.CV↗

arXiv2019

An Algorithm for Graph-Fused Lasso Based on Graph Decomposition

This work proposes a new algorithm for solving the graph-fused lasso (GFL), a method for parameter estimation that operates under the assumption that the signal tends to be locally constant over a predefined graph structure. The proposed method applies the alternating direction method of multipliers (ADMM) algorithm and is based on the decomposition of the objective function into two components. While ADMM has been widely used in this problem, existing works such as network lasso decompose the objective function into the loss function component and the total variation penalty component. In comparison, this work proposes to decompose the objective function into two components, where one component is the loss function plus part of the total variation penalty, and the other component is the remaining total variation penalty. Compared with the network lasso algorithm, this method has a smaller computational cost per iteration and converges faster in most simulations numerically.

math.OC↗

arXiv2019

Cascaded Revision Network for Novel Object Captioning

Image captioning, a challenging task where the machine automatically describes an image by sentences, has drawn significant attention in recent years. Despite the remarkable improvements of recent approaches, however, these methods are built upon a large set of training image-sentence pairs. The expensive labor efforts hence limit the captioning model to describe the wider world. In this paper, we present a novel network structure, Cascaded Revision Network, which aims at relieving the problem by equipping the model with out-of-domain knowledge. CRN first tries its best to describe an image using the existing vocabulary from in-domain knowledge. Due to the lack of out-of-domain knowledge, the caption may be inaccurate or include ambiguous words for the image with unknown (novel) objects. We propose to re-edit the primary captioning sentence by a series of cascaded operations. We introduce a perplexity predictor to find out which words are most likely to be inaccurate given the input image. Thereafter, we utilize external knowledge from a pre-trained object detection model and select more accurate words from detection results by the visual matching module. In the last step, we design a semantic matching module to ensure that the novel object is fit in the right position. By this novel cascaded captioning-revising mechanism, CRN can accurately describe images with unseen objects. We validate the proposed method with state-of-the-art performance on the held-out MSCOCO dataset as well as scale to ImageNet, demonstrating the effectiveness of this method.

cs.MM↗

arXiv2019

Learning to Adapt Invariance in Memory for Person Re-identification

This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t. three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP could facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.

cs.CV↗