arXiv subjects

Jie Cao

Publications and source records attributed to Jie Cao.

At least 127 records · Page 7Linked to original sources

arXiv2022

Ultralow loss hollow-core negative curvature fibers with nested elliptical antiresonance tubes

Hollow-core negative curvature fibers can confine light within air core and have small nonlinearity and dispersion and high damage threshold, thereby attracting a great deal of interest in the field of hollow core fibers. However, reducing the loss of hollow-core negative curvature fibers is a serious problem. On this basis, three new types of fibers with different nested tube structures are proposed in the near-infrared spectral regions and compared in detail with a previously proposed hollow-core negative curvature fiber. We used finite-element method for numerical simulation studies of their transmission loss, bending loss, and single-mode performance, and then the transmission performance of various structural fibers is compared. We found that the nested elliptical antiresonant fiber 1 has better transmission performance than that of the three other types of fibers in the spectral range of 0.72-1.6 μm. Results show that the transmission loss of the LP01 mode is as low as 6.45*10-6 dB/km at λ = 1.06 μm. To the best of our knowledge, the record low level of transmission loss of hollow-core antiresonant fibers with nested tube structures was created. In addition, the nested elliptical antiresonant fiber 1 has better bending resistance, and its bending loss was below 2.99*10-2 dB/km at 5 cm bending radius.

physics.optics↗

arXiv2022

Styleverse: Towards Identity Stylization across Heterogeneous Domains

We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains. IDS focuses on stylizing the content identity, rather than completely swapping it using the reference identity. We use an effective heterogeneous-network-based framework $Styleverse$ that uses a single domain-aware generator to exploit the Metaverse of diverse heterogeneous faces, based on the proposed dataset FS13 with limited data. FS13 means 13 kinds of Face Styles considering diverse lighting conditions, art representations and life dimensions. Previous similar tasks, \eg, image style transfer can handle textural style transfer based on a reference image. This task usually ignores the high structure-aware facial area and high-fidelity preservation of the content. However, Styleverse intends to controllably create topology-aware faces in the Parallel Style Universe, where the source facial identity is adaptively styled via AdaIN guided by the domain-aware and reference-aware style embeddings from heterogeneous pretrained models. We first establish the IDS quantitative benchmark as well as the qualitative Styleverse matrix. Extensive experiments demonstrate that Styleverse achieves higher-fidelity identity stylization compared with other state-of-the-art methods.

cs.CV↗

arXiv2021

Omnidirectional ghost imaging system and unwrapping-free panoramic ghost imaging

Ghost imaging (GI) is a novel imaging method, which can reconstruct the object information by the light intensity correlation measurements. However, at present, the field of view (FOV) is limited to the illuminating range of the light patterns. To enlarge FOV of GI efficiently, here we proposed the omnidirectional ghost imaging system (OGIS), which can achieve a 360° omnidirectional FOV at one shot only by adding a curved mirror. Moreover, by designing the retina-like annular patterns with log-polar patterns, OGIS can obtain unwrapping-free undistorted panoramic images with uniform resolution, which opens up a new way for the application of GI.

physics.optics↗

arXiv2021

Complementary Fourier single-pixel imaging

Single-pixel imaging, with the advantages of a wide spectrum, beyond-visual-field imaging, and robustness to light scattering, has attracted increasing attention in recent years. Fourier single-pixel imaging (FSI) can reconstruct sharp images under sub-Nyquist sampling. However, the conventional FSI has difficulty with balancing the imaging quality and efficiency. To overcome this issue, we proposed a novel approach called complementary Fourier single-pixel imaging (CFSI) to reduce measurements while retaining its robustness. The complementary nature of Fourier patterns based on a four-step phase-shift algorithm is combined with the complementary nature of a digital micromirror device. CFSI only requires two phase-shifted patterns to obtain one Fourier spectral value. Four light intensity values are obtained by load the two patterns, and the spectral value is calculated through differential measurement, which has good robustness to noise. The proposed method is verified by simulations and experiments compared with FSI based on two-, three-, and four-step phase shift algorithms. CFSI performed better than the other methods under the condition that the best imaging quality of CFSI is not reached. The reported technique provides an alternative approach to realize real-time and high-quality imaging.

eess.IV↗

arXiv2021

Optimization of retina-like illumination patterns in ghost imaging

Ghost imaging (GI) reconstructs images using a single-pixel or bucket detector, which has the advantages of scattering robustness, wide spectrum and beyond-visual-field imaging. However, this technique needs large amount of measurements to obtain a sharp image. There have been a lot of methods proposed to overcome this disadvantage. Retina-like patterns, as one of the compressive sensing approaches, enhance the imaging quality of region of interest (ROI) while not increase measurements. The design of the retina-like patterns determines the performance of the ROI in the reconstructed image. Unlike the conventional method to fill in ROI with random patterns, we propose to optimize retina-like patterns by filling in the ROI with the patterns containing the sparsity prior of objects. This proposed method is verified by simulations and experiments compared with conventional GI, retina-like GI and GI using patterns optimized by principal component analysis. The method using optimized retina-like patterns obtain the best imaging quality in ROI than other methods. Meanwhile, the good generalization ability of the optimized retina-like pattern is also verified. While designing the size and position of the ROI of retina-like pattern, the feature information of the target can be obtained to optimize the pattern of ROI. This proposed method paves the way for realizing high-quality GI.

eess.IV↗

arXiv2021

Database Workload Characterization with Query Plan Encoders

Smart databases are adopting artificial intelligence (AI) technologies to achieve {\em instance optimality}, and in the future, databases will come with prepackaged AI models within their core components. The reason is that every database runs on different workloads, demands specific resources, and settings to achieve optimal performance. It prompts the necessity to understand workloads running in the system along with their features comprehensively, which we dub as workload characterization. To address this workload characterization problem, we propose our query plan encoders that learn essential features and their correlations from query plans. Our pretrained encoders capture the {\em structural} and the {\em computational performance} of queries independently. We show that our pretrained encoders are adaptable to workloads that expedite the transfer learning process. We performed independent assessments of structural encoder and performance encoders with multiple downstream tasks. For the overall evaluation of our query plan encoders, we architect two downstream tasks (i) query latency prediction and (ii) query classification. These tasks show the importance of feature-based workload characterization. We also performed extensive experiments on individual encoders to verify the effectiveness of representation learning and domain adaptability.

cs.DB↗

arXiv2021

Non-uniform continuity on initial data for the two-component b-family system in Besov space

In this paper, we consider the Cauchy problem of a two-component b-family system, which includes the two-component Camassa-Holm system and the two-component Degasperis-Procesi system. It is shown that the solution map of the two-component b-family system is not uniformly continuous on the initial data in Besov spaces $B_{p, r}^{s-1}(\mathbb{R})\times B_{p, r}^s(\mathbb{R})$ with $s>\max\{1+\frac{1}{p}, \frac{3}{2}\}$, $1\leq p, r< \infty$. Our result covers and extends the previous non-uniform continuity in Sobolev spaces $H^{s-1}(\mathbb{R})\times H^s(\mathbb{R})$ for $s>\frac{5}{2}$ (Nonlinear Anal., 2014) to Besov spaces.

math.AP↗

arXiv2021

PersonalityGate: A General Plug-and-Play GNN Gate to Enhance Cascade Prediction with Personality Recognition Task

Cascade prediction estimates the size or the state of a cascade from either microscope or macroscope. It is of paramount importance for understanding the information diffusion process such as the spread of rumors and the propagation of new technologies in social networks. Recently, instead of extracting hand-crafted features or embedding cascade sequences into feature vectors for cascade prediction, graph neural networks (GNNs) are introduced to utilize the network structure which governs the cascade effect. However, these models do not take into account social factors such as personality traits which drive human's participation in the information diffusion process. In this work, we propose a novel multitask framework for enhancing cascade prediction with a personality recognition task. Specially, we design a general plug-and-play GNN gate, named PersonalityGate, to couple into existing GNN-based cascade prediction models to enhance their effectiveness and extract individuals' personality traits jointly. Experimental results on two real-world datasets demonstrate the effectiveness of our proposed framework in enhancing GNN-based cascade prediction models and in predicting individuals' personality traits as well.

cs.SI↗

arXiv2021

ReMix: Towards Image-to-Image Translation with Limited Data

Image-to-image (I2I) translation methods based on generative adversarial networks (GANs) typically suffer from overfitting when limited training data is available. In this work, we propose a data augmentation method (ReMix) to tackle this issue. We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples. The generator learns to translate the in-between samples rather than memorizing the training set, and thereby forces the discriminator to generalize. The proposed approach effectively reduces the ambiguity of generation and renders content-preserving results. The ReMix method can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ReMix method achieve significant improvements.

cs.CV↗

arXiv2020

Learning 3D Human Shape and Pose from Dense Body Parts

Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from images to the model space is highly non-linear and the rotation-based pose representation of body models is prone to result in the drift of joint positions. In this work, we investigate learning 3D human shape and pose from dense correspondences of body parts and propose a Decompose-and-aggregate Network (DaNet) to address these issues. DaNet adopts the dense correspondence maps, which densely build a bridge between 2D pixels and 3D vertices, as intermediate representations to facilitate the learning of 2D-to-3D mapping. The prediction modules of DaNet are decomposed into one global stream and multiple local streams to enable global and fine-grained perceptions for the shape and pose predictions, respectively. Messages from local streams are further aggregated to enhance the robust prediction of the rotation-based poses, where a position-aided rotation feature refinement strategy is proposed to exploit spatial relationships between body joints. Moreover, a Part-based Dropout (PartDrop) strategy is introduced to drop out dense information from intermediate representations during training, encouraging the network to focus on more complementary body parts as well as neighboring position features. The efficacy of the proposed method is validated on both indoor and real-world datasets including Human3.6M, UP3D, COCO, and 3DPW, showing that our method could significantly improve the reconstruction performance in comparison with previous state-of-the-art methods. Our code is publicly available at https://hongwenzhang.github.io/dense2mesh .

cs.CV↗

arXiv2020

BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification

Few-shot learning for fine-grained image classification has gained recent attention in computer vision. Among the approaches for few-shot learning, due to the simplicity and effectiveness, metric-based methods are favorably state-of-the-art on many tasks. Most of the metric-based methods assume a single similarity measure and thus obtain a single feature space. However, if samples can simultaneously be well classified via two distinct similarity measures, the samples within a class can distribute more compactly in a smaller feature space, producing more discriminative feature maps. Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures. After the support images and the query images pass through the convolution-based embedding module, the bi-similarity module learns feature maps according to two similarity measures of diverse characteristics. In this way, the model is enabled to learn more discriminative and less similarity-biased features from few shots of fine-grained images, such that the model generalization ability can be significantly improved. Through extensive experiments by slightly modifying established metric/similarity based networks, we show that the proposed approach produces a substantial improvement on several fine-grained image benchmark datasets. Codes are available at: https://github.com/spraise/BSNet

cs.CV↗

arXiv2020

Non-uniform continuous dependence on initial data for a two_component Novikov system in Besov space

In this paper, we show that the solution map of the two-component Novikov system is not uniformly continuous on the initial data in Besov spaces $B_{p, r}^{s-1}(\mathbb{R})\times B_{p, r}^s(\mathbb{R})$ with $s>\max\{1+\frac{1}{p}, \frac{3}{2}\}$, $1\leq p< \infty$, $1\leq r<\infty$. Our result covers and extends the previous non-uniform continuity in Sobolev spaces $H^{s-1}(\mathbb{R})\times H^s(\mathbb{R})$ for $s>\frac{5}{2}$ (J. Math. Phys., 2017) to Besov spaces.

math.AP↗

arXiv2020

$P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation

We propose an augmented Parallel-Pyramid Net ($P^2~Net$) with feature refinement by dilated bottleneck and attention module. During data preprocessing, we proposed a differentiable auto data augmentation ($DA^2$) method. We formulate the problem of searching data augmentaion policy in a differentiable form, so that the optimal policy setting can be easily updated by back propagation during training. $DA^2$ improves the training efficiency. A parallel-pyramid structure is followed to compensate the information loss introduced by the network. We innovate two fusion structures, i.e. Parallel Fusion and Progressive Fusion, to process pyramid features from backbone network. Both fusion structures leverage the advantages of spatial information affluence at high resolution and semantic comprehension at low resolution effectively. We propose a refinement stage for the pyramid features to further boost the accuracy of our network. By introducing dilated bottleneck and attention module, we increase the receptive field for the features with limited complexity and tune the importance to different feature channels. To further refine the feature maps after completion of feature extraction stage, an Attention Module ($AM$) is defined to extract weighted features from different scale feature maps generated by the parallel-pyramid structure. Compared with the traditional up-sampling refining, $AM$ can better capture the relationship between channels. Experiments corroborate the effectiveness of our proposed method. Notably, our method achieves the best performance on the challenging MSCOCO and MPII datasets.

cs.CV↗

arXiv2020

Informative Sample Mining Network for Multi-Domain Image-to-Image Translation

The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models. Existing approaches can use a unified model to achieve translations between all the visual domains. However, their outcomes are far from satisfying when there are large domain variations. In this paper, we reveal that improving the sample selection strategy is an effective solution. To select informative samples, we dynamically estimate sample importance during the training of Generative Adversarial Networks, presenting Informative Sample Mining Network. We theoretically analyze the relationship between the sample importance and the prediction of the global optimal discriminator. Then a practical importance estimation function for general conditions is derived. Furthermore, we propose a novel multi-stage sample training scheme to reduce sample hardness while preserving sample informativeness. Extensive experiments on a wide range of specific image-to-image translation tasks are conducted, and the results demonstrate our superiority over current state-of-the-art methods.

cs.CV↗

arXiv2020

Reference-guided Face Component Editing

Face portrait editing has achieved great progress in recent years. However, previous methods either 1) operate on pre-defined face attributes, lacking the flexibility of controlling shapes of high-level semantic facial components (e.g., eyes, nose, mouth), or 2) take manually edited mask or sketch as an intermediate representation for observable changes, but such additional input usually requires extra efforts to obtain. To break the limitations (e.g. shape, mask or sketch) of the existing methods, we propose a novel framework termed r-FACE (Reference-guided FAce Component Editing) for diverse and controllable face component editing with geometric changes. Specifically, r-FACE takes an image inpainting model as the backbone, utilizing reference images as conditions for controlling the shape of face components. In order to encourage the framework to concentrate on the target face components, an example-guided attention module is designed to fuse attention features and the target face component features extracted from the reference image. Through extensive experimental validation and comparisons, we verify the effectiveness of the proposed framework.

cs.CV↗

arXiv2020

ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Codes are available at https://github.com/liyunyu08/ReMarNet.

cs.CV↗

arXiv2020

OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer

A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative features from small-sample data is becoming a new trend. To this end, this paper aims to find a subspace of neural networks that can facilitate a large decision margin. Specifically, we propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain orthogonal during both the training and test processes. The Rademacher complexity of a network using the OSL is only $\frac{1}{K}$, where $K$ is the number of classes, of that of a network using the fully connected classification layer, leading to a tighter generalization error bound. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets, as well as its applicability to large-sample datasets. Codes are available at: https://github.com/dongliangchang/OSLNet.

cs.CV↗

arXiv2020

Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation

The target of human pose estimation is to determine body part or joint locations of each person from an image. This is a challenging problems with wide applications. To address this issue, this paper proposes an augmented parallel-pyramid net with attention partial module and differentiable auto-data augmentation. Technically, a parallel pyramid structure is proposed to compensate the loss of information. We take the design of parallel structure for reverse compensation. Meanwhile, the overall computational complexity does not increase. We further define an Attention Partial Module (APM) operator to extract weighted features from different scale feature maps generated by the parallel pyramid structure. Compared with refining through upsampling operator, APM can better capture the relationship between channels. At last, we proposed a differentiable auto data augmentation method to further improve estimation accuracy. We define a new pose search space where the sequences of data augmentations are formulated as a trainable and operational CNN component. Experiments corroborate the effectiveness of our proposed method. Notably, our method achieves the top-1 accuracy on the challenging COCO keypoint benchmark and the state-of-the-art results on the MPII datasets.

cs.CV↗