arXiv subjects

Bo Jiang

Publications and source records attributed to Bo Jiang.

At least 271 records · Page 15Linked to original sources

arXiv2022

Spiking GATs: Learning Graph Attentions via Spiking Neural Network

Graph Attention Networks (GATs) have been intensively studied and widely used in graph data learning tasks. Existing GATs generally adopt the self-attention mechanism to conduct graph edge attention learning, requiring expensive computation. It is known that Spiking Neural Networks (SNNs) can perform inexpensive computation by transmitting the input signal data into discrete spike trains and can also return sparse outputs. Inspired by the merits of SNNs, in this work, we propose a novel Graph Spiking Attention Network (GSAT) for graph data representation and learning. In contrast to self-attention mechanism in existing GATs, the proposed GSAT adopts a SNN module architecture which is obvious energy-efficient. Moreover, GSAT can return sparse attention coefficients in natural and thus can perform feature aggregation on the selective neighbors which makes GSAT perform robustly w.r.t graph edge noises. Experimental results on several datasets demonstrate the effectiveness, energy efficiency and robustness of the proposed GSAT model.

cs.NE↗

arXiv2022

Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search

To track the target in a video, current visual trackers usually adopt greedy search for target object localization in each frame, that is, the candidate region with the maximum response score will be selected as the tracking result of each frame. However, we found that this may be not an optimal choice, especially when encountering challenging tracking scenarios such as heavy occlusion and fast motion. To address this issue, we propose to maintain multiple tracking trajectories and apply beam search strategy for visual tracking, so that the trajectory with fewer accumulated errors can be identified. Accordingly, this paper introduces a novel multi-agent reinforcement learning based beam search tracking strategy, termed BeamTracking. It is mainly inspired by the image captioning task, which takes an image as input and generates diverse descriptions using beam search algorithm. Accordingly, we formulate the tracking as a sample selection problem fulfilled by multiple parallel decision-making processes, each of which aims at picking out one sample as their tracking result in each frame. Each maintained trajectory is associated with an agent to perform the decision-making and determine what actions should be taken to update related information. When all the frames are processed, we select the trajectory with the maximum accumulated score as the tracking result. Extensive experiments on seven popular tracking benchmark datasets validated the effectiveness of the proposed algorithm.

cs.CV↗

arXiv2022

Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification

Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classification is how to learn (1) consistent representations for images in both support and query sets and (2) effective metric learning for images between support and query sets. In this paper, we show that the two challenges can be well modeled simultaneously via a unified Query-Support TransFormer (QSFormer) model. To be specific,the proposed QSFormer involves global query-support sample Transformer (sampleFormer) branch and local patch Transformer (patchFormer) learning branch. sampleFormer aims to capture the dependence of samples in support and query sets for image representation. It adopts the Encoder, Decoder and Cross-Attention to respectively model the Support, Query (image) representation and Metric learning for few-shot classification task. Also, as a complementary to global learning branch, we adopt a local patch Transformer to extract structural representation for each image sample by capturing the long-range dependence of local image patches. In addition, a novel Cross-scale Interactive Feature Extractor (CIFE) is proposed to extract and fuse multi-scale CNN features as an effective backbone module for the proposed few-shot learning method. All modules are integrated into a unified framework and trained in an end-to-end manner. Extensive experiments on four popular datasets demonstrate the effectiveness and superiority of the proposed QSFormer.

cs.CV↗

arXiv2022

HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction

In this report, we introduce our solution to the Occupancy and Flow Prediction challenge in the Waymo Open Dataset Challenges at CVPR 2022, which ranks 1st on the leaderboard. We have developed a novel hierarchical spatial-temporal network featured with spatial-temporal encoders, a multi-scale aggregator enriched with latent variables, and a recursive hierarchical 3D decoder. We use multiple losses including focal loss and modified flow trace loss to efficiently guide the training process. Our method achieves a Flow-Grounded Occupancy AUC of 0.8389 and outperforms all the other teams on the leaderboard.

cs.CV↗

arXiv2022

Varying Coefficient Model via Adaptive Spline Fitting

The varying coefficient model has received broad attention from researchers as it is a powerful dimension reduction tool for non-parametric modeling. Most existing varying coefficient models fitted with polynomial spline assume equidistant knots and take the number of knots as the hyperparameter. However, imposing equidistant knots appears to be too rigid, and determining the optimal number of knots systematically is also a challenge. In this article, we deal with this challenge by utilizing polynomial splines with adaptively selected and predictor-specific knots to fit the coefficients in varying coefficient models. An efficient dynamic programming algorithm is proposed to find the optimal solution. Numerical results show that the new method can achieve significantly smaller mean squared errors for coefficients compared with the equidistant spline fitting method.

stat.ME↗

arXiv2022

Exploring students' backtracking behaviors in digital textbooks and its relationship to learning styles

The purpose of this study is to explore students' backtracking patterns in using a digital textbook and reveal the relationship between backtracking behaviors and academic performance as well as learning styles. The study was carried out for two semesters on 102 university students and they are required to use a digital textbook system called DITeL to review courseware. Students' backtracking behaviors are characterized by seven backtracking features extracted from interaction log data and their learning styles are measured by Felder-Silverman learning style model. The results of the study reveal that there is a subgroup of students called backtrackers who backtrack more frequently and performed better than the average students. Furthermore, the causal inference analysis reveals that a higher initial ability can directly cause a higher frequency of backtracking, thus affecting the final test score. In addition, most backtrackers are reflective and visual learners, and the seven backtracking features are good predictors in automatically identifying learning styles. Based on the results of qualitative data analysis, recommendations were made on how to provide prompt backtracking assistants and automatically detect learning styles in digital textbooks.

cs.HC↗

arXiv2022

MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking

Many RGB-T trackers attempt to attain robust feature representation by utilizing an adaptive weighting scheme (or attention mechanism). Different from these works, we propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data by adaptively adjusting the convolutional kernels for various input images in practical tracking. Given the image pairs as input, we first encode their features with the backbone network. Then, we concatenate these feature maps and generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively. Inspired by residual connection, both the generated visible and thermal feature maps will be summarized with input feature maps. The augmented feature maps will be fed into the RoI align module to generate instance-level features for subsequent classification. To address issues caused by heavy occlusion, fast motion and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target driven attention mechanism. The spatial and temporal recurrent neural network is used to capture the direction-aware context for accurate global attention prediction. Extensive experiments on three large-scale RGB-T tracking benchmark datasets validated the effectiveness of our proposed algorithm. The source code of this paper is available at \textcolor{magenta}{\url{https://github.com/wangxiao5791509/MFG_RGBT_Tracking_PyTorch}}.

cs.CV↗

arXiv2022

Unified GCNs: Towards Connecting GCNs with CNNs

Graph Convolutional Networks (GCNs) have been widely demonstrated their powerful ability in graph data representation and learning. Existing graph convolution layers are mainly designed based on graph signal processing and transform aspect which usually suffer from some limitations, such as over-smoothing, over-squashing and non-robustness, etc. As we all know that Convolution Neural Networks (CNNs) have received great success in many computer vision and machine learning. One main aspect is that CNNs leverage many learnable convolution filters (kernels) to obtain rich feature descriptors and thus can have high capacity to encode complex patterns in visual data analysis. Also, CNNs are flexible in designing their network architecture, such as MobileNet, ResNet, Xception, etc. Therefore, it is natural to arise a question: can we design graph convolutional layer as flexibly as that in CNNs? Innovatively, in this paper, we consider connecting GCNs with CNNs deeply from a general perspective of depthwise separable convolution operation. Specifically, we show that GCN and GAT indeed perform some specific depthwise separable convolution operations. This novel interpretation enables us to better understand the connections between GCNs (GCN, GAT) and CNNs and further inspires us to design more Unified GCNs (UGCNs). As two showcases, we implement two UGCNs, i.e., Separable UGCN (S-UGCN) and General UGCN (G-UGCN) for graph data representation and learning. Promising experiments on several graph representation benchmarks demonstrate the effectiveness and advantages of the proposed UGCNs.

cs.CV↗

arXiv2022

Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection

Recently, transformer-based methods have achieved promising progresses in object detection, as they can eliminate the post-processes like NMS and enrich the deep representations. However, these methods cannot well cope with scene text due to its extreme variance of scales and aspect ratios. In this paper, we present a simple yet effective transformer-based architecture for scene text detection. Different from previous approaches that learn robust deep representations of scene text in a holistic manner, our method performs scene text detection based on a few representative features, which avoids the disturbance by background and reduces the computational cost. Specifically, we first select a few representative features at all scales that are highly relevant to foreground text. Then, we adopt a transformer for modeling the relationship of the sampled features, which effectively divides them into reasonable groups. As each feature group corresponds to a text instance, its bounding box can be easily obtained without any post-processing operation. Using the basic feature pyramid network for feature extraction, our method consistently achieves state-of-the-art results on several popular datasets for scene text detection.

cs.CV↗

arXiv2022

Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling

In this paper, we consider an unconstrained optimization model where the objective is a sum of a large number of possibly nonconvex functions, though overall the objective is assumed to be smooth and convex. Our bid to solving such model uses the framework of cubic regularization of Newton's method. As well known, the crux in cubic regularization is its utilization of the Hessian information, which may be computationally expensive for large-scale problems. To tackle this, we resort to approximating the Hessian matrix via sub-sampling. In particular, we propose to compute an approximated Hessian matrix by either \textit{uniformly}\/ or \textit{non-uniformly}\/ sub-sampling the components of the objective. Based upon such sampling strategy, we develop accelerated adaptive cubic regularization approaches and provide theoretical guarantees on global iteration complexity of $O(ε^{-1/3})$ with high probability, which matches that of the original accelerated cubic regularization methods \cite{Jiang-2017-Unified} using the \textit{full}\/ Hessian information. Interestingly, we show that in the worst case scenario our algorithm still achieves an $O\left(\log(ε^{-1})ε^{-5/6}\right)$ iteration complexity bound. The performances of the proposed methods on the regularized logistic regression problems show a clear effect of acceleration in terms of the epoch counts on several real data sets.

math.OC↗

arXiv2022

Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregators

Graph neural networks (GNNs) have achieved great success in many graph learning tasks. The main aspect powering existing GNNs is the multi-layer network architecture to learn the nonlinear graph representations for the specific learning tasks. The core operation in GNNs is message propagation in which each node updates its representation by aggregating its neighbors' representations. Existing GNNs mainly adopt either linear neighborhood aggregation (mean,sum) or max aggregator in their message propagation. (1) For linear aggregators, the whole nonlinearity and network's capacity of GNNs are generally limited due to deeper GNNs usually suffer from over-smoothing issue. (2) For max aggregator, it usually fails to be aware of the detailed information of node representations within neighborhood. To overcome these issues, we re-think the message propagation mechanism in GNNs and aim to develop the general nonlinear aggregators for neighborhood information aggregation in GNNs. One main aspect of our proposed nonlinear aggregators is that they provide the optimally balanced aggregators between max and mean/sum aggregations. Thus, our aggregators can inherit both (i) high nonlinearity that increases network's capacity and (ii) detail-sensitivity that preserves the detailed information of representations together in GNNs' message propagation. Promising experiments on several datasets show the effectiveness of the proposed nonlinear aggregators.

cs.LG↗

arXiv2022

A Novel Negative $\ell_1$ Penalty Approach for Multiuser One-Bit Massive MIMO Downlink with PSK Signaling

This paper considers the one-bit precoding problem for the multiuser downlink massive multiple-input multiple-output (MIMO) system with phase shift keying (PSK) modulation and focuses on the celebrated constructive interference (CI)-based problem formulation. The existence of the discrete one-bit constraint makes the problem generally hard to solve. In this paper, we propose an efficient negative $\ell_1$ penalty approach for finding a high-quality solution of the considered problem. Specifically, we first propose a novel negative $\ell_1$ penalty model, which penalizes the one-bit constraint into the objective with a negative $\ell_1$-norm term, and show the equivalence between (global and local) solutions of the original problem and the penalty problem when the penalty parameter is sufficiently large. We further transform the penalty model into an equivalent min-max problem and propose an efficient alternating optimization (AO) algorithm for solving it. The AO algorithm enjoys low per-iteration complexity and is guaranteed to converge to the stationary point of the min-max problem. Numerical results show that, compared against the state-of-the-art CI-based algorithms, the proposed algorithm generally achieves better bit-error-rate (BER) performance with lower computational cost.

cs.IT↗

arXiv2022

A Unified Framework for Generalized Moment Problems: a Novel Primal-Dual Approach

Generalized moment problems optimize functional expectation over a class of distributions with generalized moment constraints, i.e., the function in the moment can be any measurable function. These problems have recently attracted growing interest due to their great flexibility in representing nonstandard moment constraints, such as geometry-mean constraints, entropy constraints, and exponential-type moment constraints. Despite the increasing research interest, analytical solutions are mostly missing for these problems, and researchers have to settle for nontight bounds or numerical approaches that are either suboptimal or only applicable to some special cases. In addition, the techniques used to develop closed-form solutions to the standard moment problems are tailored for specific problem structures. In this paper, we propose a framework that provides a unified treatment for any moment problem. The key ingredient of the framework is a novel primal-dual optimality condition. This optimality condition enables us to reduce the original infinite dimensional problem to a nonlinear equation system with a finite number of variables. In solving three specific moment problems, the framework demonstrates a clear path for identifying the analytical solution if one is available, otherwise, it produces semi-analytical solutions that lead to efficient numerical algorithms. Finally, through numerical experiments, we provide further evidence regarding the performance of the resulting algorithms by solving a moment problem and a distributionally robust newsvendor problem.

math.OC↗

arXiv2021

Room-temperature continuous-wave upconversion white microlaser in a rare-earth doped microcavity

White laser covering the visible color spectrum is critical in various applications including vivid display, holographic imaging and light-based version of Wi-Fi, but it is still challenging to realize the white microlaser due to the rigorous requirement in the balance between the optical gain and the feedback at different wavelengths. Here, we employ Tm, Er and Yb ions corporately for the upconversion white lasing in a single ultrahigh quality (Q) (up to 108) doped microcavity, where the thresholds of the red, green and blue lasers are about 90, 500 and 300 μW, respectively. To the best of our knowledge, it is the first rare-earth elements based room-temperature, continuous-wave white microlaser, which exhibits relatively stable chromaticity over 180 minutes, making it possible for practical applications.

physics.optics↗

arXiv2021

Kernel-based Partial Permutation Test for Detecting Heterogeneous Functional Relationship

We propose a kernel-based partial permutation test for checking the equality of functional relationship between response and covariates among different groups. The main idea, which is intuitive and easy to implement, is to keep the projections of the response vector $\boldsymbol{Y}$ on leading principle components of a kernel matrix fixed and permute $\boldsymbol{Y}$'s projections on the remaining principle components. The proposed test allows for different choices of kernels, corresponding to different classes of functions under the null hypothesis. First, using linear or polynomial kernels, our partial permutation tests are exactly valid in finite samples for linear or polynomial regression models with Gaussian noise; similar results straightforwardly extend to kernels with finite feature spaces. Second, by allowing the kernel feature space to diverge with the sample size, the test can be large-sample valid for a wider class of functions. Third, for general kernels with possibly infinite-dimensional feature space, the partial permutation test is exactly valid when the covariates are exactly balanced across all groups, or asymptotically valid when the underlying function follows certain regularized Gaussian processes. We further suggest test statistics using likelihood ratio between two (nested) GPR models, and propose computationally efficient algorithms utilizing the EM algorithm and Newton's method, where the latter also involves Fisher scoring and quadratic programming and is particularly useful when EM suffers from slow convergence. Extensions to correlated and non-Gaussian noises have also been investigated theoretically or numerically. Furthermore, the test can be extended to use multiple kernels together and can thus enjoy properties from each kernel. Both simulation study and application illustrate the properties of the proposed test.

stat.ME↗

arXiv2021

Robust Graph Data Learning via Latent Graph Convolutional Representation

Graph Convolutional Representation (GCR) has achieved impressive performance for graph data representation. However, existing GCR is generally defined on the input fixed graph which may restrict the representation capacity and also be vulnerable to the structural attacks and noises. To address this issue, we propose a novel Latent Graph Convolutional Representation (LatGCR) for robust graph data representation and learning. Our LatGCR is derived based on reformulating graph convolutional representation from the aspect of graph neighborhood reconstruction. Given an input graph $\textbf{A}$, LatGCR aims to generate a flexible latent graph $\widetilde{\textbf{A}}$ for graph convolutional representation which obviously enhances the representation capacity and also performs robustly w.r.t graph structural attacks and noises. Moreover, LatGCR is implemented in a self-supervised manner and thus provides a basic block for both supervised and unsupervised graph learning tasks. Experiments on several datasets demonstrate the effectiveness and robustness of LatGCR.

cs.CV↗

arXiv2021

Quaternion matrix decomposition and its theoretical implications

This paper proposes a novel matrix rank-one decomposition for quaternion Hermitian matrices, which admits a stronger property than the previous results in (sturm2003cones,huang2007complex,ai2011new). The enhanced property can be used to drive some improved results in joint numerical range, $\mathcal{S}$-Procedure and quadratically constrained quadratic programming (QCQP) in the quaternion domain, demonstrating the capability of our new decomposition technique.

math.OC↗

arXiv2021

STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification

Recently, Batch DropBlock network (BDB) has demonstrated its effectiveness on person image representation and re-identification task via feature erasing. However, BDB drops the features \textbf{randomly} which may lead to sub-optimal results. In this paper, we propose a novel Self-Thresholding attention guided Adaptive DropBlock network (STADB) for person re-ID which can \textbf{adaptively} erase the most discriminative regions. Specifically, STADB first obtains an attention map by channel-wise pooling and returns a drop mask by thresholding the attention map. Then, the input features and self-thresholding attention guided drop mask are multiplied to generate the dropped feature maps. In addition, STADB utilizes the spatial and channel attention to learn a better feature map and iteratively trains the feature dropping module for person re-ID. Experiments on several benchmark datasets demonstrate that the proposed STADB outperforms many other related methods for person re-ID. The source code of this paper is released at: \textcolor{red}{\url{https://github.com/wangxiao5791509/STADB_ReID}}.

cs.CV↗