arXiv subjects

Bo Jiang

Publications and source records attributed to Bo Jiang.

At least 253 records · Page 14Linked to original sources

arXiv2023

Implicit Bayes Adaptation: A Collaborative Transport Approach

The power and flexibility of Optimal Transport (OT) have pervaded a wide spectrum of problems, including recent Machine Learning challenges such as unsupervised domain adaptation. Its essence of quantitatively relating two probability distributions by some optimal metric, has been creatively exploited and shown to hold promise for many real-world data challenges. In a related theme in the present work, we posit that domain adaptation robustness is rooted in the intrinsic (latent) representations of the respective data, which are inherently lying in a non-linear submanifold embedded in a higher dimensional Euclidean space. We account for the geometric properties by refining the $l^2$ Euclidean metric to better reflect the geodesic distance between two distinct representations. We integrate a metric correction term as well as a prior cluster structure in the source data of the OT-driven adaptation. We show that this is tantamount to an implicit Bayesian framework, which we demonstrate to be viable for a more robust and better-performing approach to domain adaptation. Substantiating experiments are also included for validation purposes.

eess.IV↗

arXiv2023

MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either adopt the Cross-Attention (CA) mechanism or simple concatenation to achieve the information interaction among different modalities which generally ignore the issue of modality gap. In this work, we re-think Transformer and extend it to MutualFormer for multi-modality data representation. Rather than CA in Transformer, MutualFormer employs our new design of Cross-Diffusion Attention (CDA) to conduct the information communication among different modalities. Comparing with CA, the main advantages of the proposed CDA are three aspects. First, the crossaffinities in CDA are defined based on the individual modality affinities in the metric space which thus can naturally avoid the issue of modality/domain gap in feature based CA definition. Second, CDA provides a general scheme which can either be used for multimodality representation or serve as the post-optimization for existing CA models. Third, CDA is implemented efficiently. We successfully apply the MutualFormer on different multi-modality learning tasks (i.e., RGB-Depth SOD, RGB-NIR object ReID). Extensive experiments demonstrate the effectiveness of the proposed MutualFormer.

cs.CV↗

arXiv2023

Approximating Tensor Norms via Sphere Covering: Bridging the Gap Between Primal and Dual

The matrix spectral and nuclear norms appear in enormous applications. The generalizations of these norms to higher-order tensors is becoming increasingly important but unfortunately they are NP-hard to compute or even approximate. Although the two norms are dual to each other, the best known approximation bound achieved by polynomial-time algorithms for the tensor nuclear norm is worse than that for the tensor spectral norm. In this paper, we bridge this gap by proposing deterministic algorithms with the best bound for both tensor norms. Our methods not only improve the approximation bound for the nuclear norm, but are also data independent and easily implementable comparing to existing approximation methods for the tensor spectral norm. The main idea is to construct a selection of unit vectors that can approximately represent the unit sphere, in other words, a collection of spherical caps to cover the sphere. For this purpose, we explicitly construct several collections of spherical caps for sphere covering with adjustable parameters for different levels of approximations and cardinalities. These readily available constructions are of independent interest as they provide a powerful tool for various decision making problems on spheres and related problems. We believe the ideas of constructions and the applications to approximate tensor norms can be useful to tackle optimization problems over other sets such as the binary hypercube.

math.OC↗

arXiv2023

Efficient Quantized Constant Envelope Precoding for Multiuser Downlink Massive MIMO Systems

Quantized constant envelope (QCE) precoding, a new transmission scheme that only discrete QCE transmit signals are allowed at each antenna, has gained growing research interests due to its ability of reducing the hardware cost and the energy consumption of massive multiple-input multiple-output (MIMO) systems. However, the discrete nature of QCE transmit signals greatly complicates the precoding design. In this paper, we consider the QCE precoding problem for a massive MIMO system with phase shift keying (PSK) modulation and develop an efficient approach for solving the constructive interference (CI) based problem formulation. Our approach is based on a custom-designed (continuous) penalty model that is equivalent to the original discrete problem. Specifically, the penalty model relaxes the discrete QCE constraint and penalizes it in the objective with a negative $\ell_2$-norm term, which leads to a non-smooth non-convex optimization problem. To tackle it, we resort to our recently proposed alternating optimization (AO) algorithm. We show that the AO algorithm admits closed-form updates at each iteration when applied to our problem and thus can be efficiently implemented. Simulation results demonstrate the superiority of the proposed approach over the existing algorithms.

cs.IT↗

arXiv2023

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concerns. Instead, this paper considers a realistic problem setting called source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain. For the challenging problem, we first construct a teacher-student learning baseline by stabilizing the predictions under data augmentation and network ensembles. Built on this, we further propose a unified approach, Mixup Augmentation and Progressive Selection (MAPS), to fully exploit the noisy pseudo labels of unlabeled target data during training. On the one hand, MAPS regularizes the model to favor simple linear behavior in-between the target samples via self-mixup augmentation, preventing the model from over-fitting to noisy predictions. On the other hand, MAPS employs the self-paced learning paradigm and progressively selects pseudo-labeled samples from `easy' to `hard' into the training process to reduce noise accumulation. Results on four keypoint detection datasets show that MAPS outperforms the baseline and achieves comparable or even better results in comparison to previous non-source-free counterparts.

cs.CV↗

arXiv2023

Flexible Alignment Super-Resolution Network for Multi-Contrast MRI

Magnetic resonance imaging plays an essential role in clinical diagnosis by acquiring the structural information of biological tissue. Recently, many multi-contrast MRI super-resolution networks achieve good effects. However, most studies ignore the impact of the inappropriate foreground scale and patch size of multi-contrast MRI, which probably leads to inappropriate feature alignment. To tackle this problem, we propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast MRI Super-Resolution. The Flexible Alignment module of FASR-Net consists of two modules for feature alignment. (1) The Single-Multi Pyramid Alignment(S-A) module solves the situation where low-resolution (LR) images and reference (Ref) images have different scales. (2) The Multi-Multi Pyramid Alignment(M-A) module solves the situation where LR and Ref images have the same scale. Besides, we propose the Cross-Hierarchical Progressive Fusion (CHPF) module aiming at fusing the features effectively, further improving the image quality. Compared with other state-of-the-art methods, FASR-net achieves the most competitive results on FastMRI and IXI datasets. Our code will be available at \href{https://github.com/yimingliu123/FASR-Net}{https://github.com/yimingliu123/FASR-Net}.

eess.IV↗

arXiv2023

Understanding the convergence of the preconditioned PDHG method: a view of indefinite proximal ADMM

The primal-dual hybrid gradient (PDHG) algorithm is popular in solving min-max problems which are being widely used in a variety of areas. To improve the applicability and efficiency of PDHG for different application scenarios, we focus on the preconditioned PDHG (PrePDHG) algorithm, which is a framework covering PDHG, alternating direction method of multipliers (ADMM), and other methods. We give the optimal convergence condition of PrePDHG in the sense that the key parameters in the condition can not be further improved, which fills the theoretical gap in the-state-of-art convergence results of PrePDHG, and obtain the ergodic and non-ergodic sublinear convergence rates of PrePDHG. The theoretical analysis is achieved by establishing the equivalence between PrePDHG and indefinite proximal ADMM. Besides, we discuss various choices of the proximal matrices in PrePDHG and derive some interesting results. For example, the convergence condition of diagonal PrePDHG is improved to be tight, the dual stepsize of the balanced augmented Lagrangian method can be enlarged to $4/3$ from $1$, and a balanced augmented Lagrangian method with symmetric Gauss-Seidel iterations is also explored. Numerical results on the matrix game, projection onto the Birkhoff polytope, earth mover's distance, and CT reconstruction verify the effectiveness and superiority of PrePDHG.

math.OC↗

arXiv2023

FuncPipe: A Pipelined Serverless Framework for Fast and Cost-efficient Training of Deep Learning Models

Training deep learning (DL) models in the cloud has become a norm. With the emergence of serverless computing and its benefits of true pay-as-you-go pricing and scalability, systems researchers have recently started to provide support for serverless-based training. However, the ability to train DL models on serverless platforms is hindered by the resource limitations of today's serverless infrastructure and DL models' explosive requirement for memory and bandwidth. This paper describes FuncPipe, a novel pipelined training framework specifically designed for serverless platforms that enable fast and low-cost training of DL models. FuncPipe is designed with the key insight that model partitioning can be leveraged to bridge both memory and bandwidth gaps between the capacity of serverless functions and the requirement of DL training. Conceptually simple, we have to answer several design questions, including how to partition the model, configure each serverless function, and exploit each function's uplink/downlink bandwidth. In particular, we tailor a micro-batch scheduling policy for the serverless environment, which serves as the basis for the subsequent optimization. Our Mixed-Integer Quadratic Programming formulation automatically and simultaneously configures serverless resources and partitions models to fit within the resource constraints. Lastly, we improve the bandwidth efficiency of storage-based synchronization with a novel pipelined scatter-reduce algorithm. We implement FuncPipe on two popular cloud serverless platforms and show that it achieves 7%-77% cost savings and 1.3X-2.2X speedup compared to state-of-the-art serverless-based frameworks.

cs.DC↗

arXiv2022

Complexity and computation for the spectral norm and nuclear norm of order three tensors with one fixed dimension

The recent decade has witnessed a surge of research in modelling and computing from two-way data (matrices) to multiway data (tensors). However, there is a drastic phase transition for most tensor optimization problems when the order of a tensor increases from two (a matrix) to three: Most tensor problems are NP-hard while that for matrices are easy. It triggers a question on where exactly the transition occurs. The paper aims to study this kind of question for the spectral norm and the nuclear norm. Although computing the spectral norm for a general $\ell\times m\times n$ tensor is NP-hard, we show that it can be computed in polynomial time if $\ell$ is fixed. This is the same for the nuclear norm. While these polynomial-time methods are not implementable in practice, we propose fully polynomial-time approximation schemes (FPTAS) for the spectral norm based on spherical grids and for the nuclear norm with further help of duality theory and semidefinite optimization. Numerical experiments on simulated data show that our FPTAS can compute these tensor norms for small $\ell \le 6$ but large $m, n\ge50$. To the best of our knowledge, this is the first method that can compute the nuclear norm of general asymmetric tensors. Both our polynomial-time algorithms and FPTAS can be extended to higher-order tensors as well.

math.OC↗

arXiv2022

Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction

Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first end-to-end Transformer-based framework which jointly and interactively performs online mapping, object detection and motion prediction. PIP leverages map queries, agent queries and mode queries to encode the instance-wise information of map elements, agents and motion intentions, respectively. Based on the unified query representation, a differentiable multi-task interaction scheme is proposed to exploit the correlation between perception and prediction. Even without human-annotated HD map or agent's historical tracking trajectory as guidance information, PIP realizes end-to-end multi-agent motion prediction and achieves better performance than tracking-based and HD-map-based methods. PIP provides comprehensive high-level information of the driving scene (vectorized static map and dynamic objects with motion information), and contributes to the downstream planning and control. Code and models will be released for facilitating further research.

cs.CV↗

arXiv2022

A Riemannian exponential augmented Lagrangian method for computing the projection robust Wasserstein distance

Projecting the distance measures onto a low-dimensional space is an efficient way of mitigating the curse of dimensionality in the classical Wasserstein distance using optimal transport. The obtained maximized distance is referred to as projection robust Wasserstein (PRW) distance. In this paper, we equivalently reformulate the computation of the PRW distance as an optimization problem over the Cartesian product of the Stiefel manifold and the Euclidean space with additional nonlinear inequality constraints. We propose a Riemannian exponential augmented Lagrangian method (ReALM) with a global convergence guarantee to solve this problem. Compared with the existing approaches, ReALM can potentially avoid too small penalty parameters. Moreover, we propose a framework of inexact Riemannian gradient descent methods to solve the subproblems in ReALM efficiently. In particular, by using the special structure of the subproblem, we give a practical algorithm named as the inexact Riemannian Barzilai-Borwein method with Sinkhorn iteration (iRBBS). The remarkable features of iRBBS lie in that it performs a flexible number of Sinkhorn iterations to compute an inexact gradient with respect to the projection matrix of the problem and adopts the Barzilai-Borwein stepsize based on the inexact gradient information to improve the performance. We show that iRBBS can return an $ε$-stationary point of the original PRW distance problem within $\mathcal{O}(ε^{-3})$ iterations. Extensive numerical results on synthetic and real datasets demonstrate that our proposed ReALM as well as iRBBS outperform the state-of-the-art solvers for computing the PRW distance.

math.OC↗

arXiv2022

Rethinking Batch Sample Relationships for Data Representation: A Batch-Graph Transformer based Approach

Exploring sample relationships within each mini-batch has shown great potential for learning image representations. Existing works generally adopt the regular Transformer to model the visual content relationships, ignoring the cues of semantic/label correlations between samples. Also, they generally adopt the "full" self-attention mechanism which are obviously redundant and also sensitive to the noisy samples. To overcome these issues, in this paper, we design a simple yet flexible Batch-Graph Transformer (BGFormer) for mini-batch sample representations by deeply capturing the relationships of image samples from both visual and semantic perspectives. BGFormer has three main aspects. (1) It employs a flexible graph model, termed Batch Graph to jointly encode the visual and semantic relationships of samples within each mini-batch. (2) It explores the neighborhood relationships of samples by borrowing the idea of sparse graph representation which thus performs robustly, w.r.t., noisy samples. (3) It devises a novel Transformer architecture that mainly adopts dual structure-constrained self-attention (SSA), together with graph normalization, FFN, etc, to carefully exploit the batch graph information for sample tokens (nodes) representations. As an application, we apply BGFormer to the metric learning tasks. Extensive experiments on four popular datasets demonstrate the effectiveness of the proposed model.

cs.CV↗

arXiv2022

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption. Meanwhile, the biologically inspired event cameras attracted great interest due to their unique features, such as high dynamic range, dense temporal but sparse spatial resolution, low latency, low power, etc. As it is a newly arising sensor, even there is no realistic large-scale dataset for HAR. Considering its great practical value, in this paper, we propose a large-scale benchmark dataset to bridge this gap, termed HARDVS, which contains 300 categories and more than 100K event sequences. We evaluate and report the performance of multiple popular HAR algorithms, which provide extensive baselines for future works to compare. More importantly, we propose a novel spatial-temporal feature learning and fusion framework, termed ESTF, for event stream based human activity recognition. It first projects the event streams into spatial and temporal embeddings using StemNet, then, encodes and fuses the dual-view representations using Transformer networks. Finally, the dual features are concatenated and fed into a classification head for activity prediction. Extensive experiments on multiple datasets fully validated the effectiveness of our model. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/HARDVS}.

cs.CV↗

arXiv2022

An efficient algorithm for the $\ell_{p}$ norm based metric nearness problem

Given a dissimilarity matrix, the metric nearness problem is to find the nearest matrix of distances that satisfy the triangle inequalities. This problem has wide applications, such as sensor networks, image processing, and so on. But it is of great challenge even to obtain a moderately accurate solution due to the $O(n^{3})$ metric constraints and the nonsmooth objective function which is usually a weighted $\ell_{p}$ norm based distance. In this paper, we propose a delayed constraint generation method with each subproblem solved by the semismooth Newton based proximal augmented Lagrangian method (PALM) for the metric nearness problem. Due to the high memory requirement for the storage of the matrix related to the metric constraints, we take advantage of the special structure of the matrix and do not need to store the corresponding constraint matrix. A pleasing aspect of our algorithm is that we can solve these problems involving up to $10^{8}$ variables and $10^{13}$ constraints. Numerical experiments demonstrate the efficiency of our algorithm. In theory, firstly, under a mild condition, we establish a primal-dual error bound condition which is very essential for the analysis of local convergence rate of PALM. Secondly, we prove the equivalence between the dual nondegeneracy condition and nonsingularity of the generalized Jacobian for the inner subproblem of PALM. Thirdly, when $q(\cdot)=\|\cdot\|_{1}$ or $\|\cdot\|_{\infty}$, without the strict complementarity condition, we also prove the equivalence between the the dual nondegeneracy condition and the uniqueness of the primal solution.

math.OC↗

arXiv2022

Refining Self-Supervised Learning in Imaging: Beyond Linear Metric

We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning. Specifically, our proposed metric may be interpreted as a dependence measure between two adapted projections learned from the so-called latent representations. This is in contrast to the cosine similarity measure in the conventional contrastive learning model, which accounts for correlation information. To the best of our knowledge, this effectively non-linearly fused information embedded in the Jaccard similarity, is novel to self-supervision learning with promising results. The proposed approach is compared to two state-of-the-art self-supervised contrastive learning methods on three image datasets. We not only demonstrate its amenable applicability in current ML problems, but also its improved performance and training efficiency.

cs.CV↗

arXiv2022

On Embeddings and Inverse Embeddings of Input Design for Regularized System Identification

Input design is an important problem for system identification and has been well studied for the classical system identification, i.e., the maximum likelihood/prediction error method. For the emerging regularized system identification, the study on input design has just started, and it is often formulated as a non-convex optimization problem that minimizes a scalar measure of the Bayesian mean squared error matrix subject to certain constraints, and the state-of-art method is the so-called quadratic mapping and inverse embedding (QMIE) method, where a time domain inverse embedding (TDIE) is proposed to find the inverse of the quadratic mapping. In this paper, we report some new results on the embeddings/inverse embeddings of the QMIE method. Firstly, we present a general result on the frequency domain inverse embedding (FDIE) that is to find the inverse of the quadratic mapping described by the discrete-time Fourier transform. Then we show the relation between the TDIE and the FDIE from a graph signal processing perspective. Finally, motivated by this perspective, we further propose a graph induced embedding and its inverse, which include the previously introduced embeddings as special cases. This deepens the understanding of input design from a new viewpoint beyond the real domain and the frequency domain viewpoints.

eess.SY↗

arXiv2022

An indefinite-proximal-based strictly contractive Peaceman-Rachford splitting method

The Peaceman-Rachford splitting method is efficient for minimizing a convex optimization problem with a separable objective function and linear constraints. However, its convergence was not guaranteed without extra requirements. He {\it et al.} (SIAM J. Optim. 24: 1011 - 1040, 2014) proved the convergence of a strictly contractive Peaceman-Rachford splitting method by employing a suitable underdetermined relaxation factor. In this paper, we further extend the so-called strictly contractive Peaceman-Rachford splitting method by using two different relaxation factors. Besides, motivated by the recent advances on the ADMM type method with indefinite proximal terms, we employ the indefinite proximal term in the strictly contractive Peaceman-Rachford splitting method. We show that the proposed indefinite-proximal strictly contractive Peaceman-Rachford splitting method is convergent and also prove the $o(1/t)$ convergence rate in the nonergodic sense. The numerical tests on the $l_1$ regularized least square problem demonstrate the efficiency of the proposed method.

math.OC↗

arXiv2022

BQA: A High-performance Quantum Circuits Scheduling Strategy Based on Heuristic Search

Currently, quantum computing is developing at a high speed because its high parallelism and high computing power bring new solutions to many fields. However, due to chip process technology, it is difficult to achieve full coupling of all qubits on a quantum chip, so when compiling a quantum circuit onto a physical chip, it is necessary to ensure that the two-qubit gate acts on a pair of coupled qubits by inserting swap gates. It will cause great additional cost when a large number of swap gates are inserted, leading to the execution time of quantum circuits longer. In this paper, we designed a way based on the business to insert swap gates BQA(Busy Qubits Avoid). We exploit the imbalance of the number of gates on qubits, trying to hide the overhead of swap gates. At the same time, we also expect swap gates to make as little negative impact on subsequent two-qubit gates as possible. We have designed a heuristic function that can take into account both of these points. Compared with qiskit, the execution time of the circuit optimized by our proposed method is only 0.5 times that of the qiskit compiled circuit. And when the number of two-qubit gates is large, it will achieve higher level than general conditions. This implies higher execution efficiency and lower decoherence error rate.

quant-ph↗