arXiv subjects

Shuai Shao

Publications and source records attributed to Shuai Shao.

At least 109 records · Page 6Linked to original sources

arXiv2023

ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst

Building general-purpose models that can perceive diverse real-world modalities and solve various tasks is an appealing target in artificial intelligence. In this paper, we present ChatBridge, a novel multimodal language model that leverages the expressive capabilities of language as the catalyst to bridge the gap between various modalities. We show that only language-paired two-modality data is sufficient to connect all modalities. ChatBridge leverages recent large language models (LLM) and extends their zero-shot capabilities to incorporate diverse multimodal inputs. ChatBridge undergoes a two-stage training. The first stage aligns each modality with language, which brings emergent multimodal correlation and collaboration abilities. The second stage instruction-finetunes ChatBridge to align it with user intent with our newly proposed multimodal instruction tuning dataset, named MULTIS, which covers a wide range of 16 multimodal tasks of text, image, video, and audio modalities. We show strong quantitative and qualitative results on zero-shot multimodal tasks covering text, image, video, and audio modalities. All codes, data, and models of ChatBridge will be open-sourced.

cs.CV↗

arXiv2023

ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition

Human activity recognition (HAR) is one of the core research themes in ubiquitous and wearable computing. With the shift to deep learning (DL) based analysis approaches, it has become possible to extract high-level features and perform classification in an end-to-end manner. Despite their promising overall capabilities, DL-based HAR may suffer from overfitting due to the notoriously small, often inadequate, amounts of labeled sample data that are available for typical HAR applications. In response to such challenges, we propose ConvBoost -- a novel, three-layer, structured model architecture and boosting framework for convolutional network based HAR. Our framework generates additional training data from three different perspectives for improved HAR, aiming to alleviate the shortness of labeled training data in the field. Specifically, with the introduction of three conceptual layers--Sampling Layer, Data Augmentation Layer, and Resilient Layer -- we develop three "boosters" -- R-Frame, Mix-up, and C-Drop -- to enrich the per-epoch training data by dense-sampling, synthesizing, and simulating, respectively. These new conceptual layers and boosters, that are universally applicable for any kind of convolutional network, have been designed based on the characteristics of the sensor data and the concept of frame-wise HAR. In our experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, GOTOV) we demonstrate the effectiveness of our ConvBoost framework for HAR applications based on variants of convolutional networks: vanilla CNN, ConvLSTM, and Attention Models. We achieved substantial performance gains for all of them, which suggests that the proposed approach is generic and can serve as a practical solution for boosting the performance of existing ConvNet-based HAR models. This is an open-source project, and the code can be found at https://github.com/sshao2013/ConvBoost

cs.LG↗

arXiv2022

Simple Yet Surprisingly Effective Training Strategies for LSTMs in Sensor-Based Human Activity Recognition

Human Activity Recognition (HAR) is one of the core research areas in mobile and wearable computing. With the application of deep learning (DL) techniques such as CNN, recognizing periodic or static activities (e.g, walking, lying, cycling, etc.) has become a well studied problem. What remains a major challenge though is the sporadic activity recognition (SAR) problem, where activities of interest tend to be non periodic, and occur less frequently when compared with the often large amount of irrelevant background activities. Recent works suggested that sequential DL models (such as LSTMs) have great potential for modeling nonperiodic behaviours, and in this paper we studied some LSTM training strategies for SAR. Specifically, we proposed two simple yet effective LSTM variants, namely delay model and inverse model, for two SAR scenarios (with and without time critical requirement). For time critical SAR, the delay model can effectively exploit predefined delay intervals (within tolerance) in form of contextual information for improved performance. For regular SAR task, the second proposed, inverse model can learn patterns from the time series in an inverse manner, which can be complementary to the forward model (i.e.,LSTM), and combining both can boost the performance. These two LSTM variants are very practical, and they can be deemed as training strategies without alteration of the LSTM fundamentals. We also studied some additional LSTM training strategies, which can further improve the accuracy. We evaluated our models on two SAR and one non-SAR datasets, and the promising results demonstrated the effectiveness of our approaches in HAR applications.

eess.SP↗

arXiv2022

A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy

Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio. Previous work has shown that a neural AEC model operating on log-mel spectral features (denoted "logmel" hereafter) can greatly improve Automatic Speech Recognition (ASR) accuracy when optimized with an auxiliary loss utilizing a pre-trained ASR model encoder. In this paper, we develop a conformer-based waveform-domain neural AEC model inspired by the "TasNet" architecture. The model is trained by jointly optimizing Negative Scale-Invariant SNR (SISNR) and ASR losses on a large speech dataset. On a realistic rerecorded test set, we find that cascading a linear adaptive AEC and a waveform-domain neural AEC is very effective, giving 56-59% word error rate (WER) reduction over the linear AEC alone. On this test set, the 1.6M parameter waveform-domain neural AEC also improves over a larger 6.5M parameter logmel-domain neural AEC model by 20-29% in easy to moderate conditions. By operating on smaller frames, the waveform neural model is able to perform better at smaller sizes and is better suited for applications where memory is limited.

eess.AS↗

arXiv2022

Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation

Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. Present UDA models focus on alleviating the domain shift by minimizing the feature discrepancy between the source domain and the target domain but usually ignore the class confusion problem. In this work, we propose an Inter-class Separation and Intra-class Aggregation (ISIA) mechanism. It encourages the cross-domain representative consistency between the same categories and differentiation among diverse categories. In this way, the features belonging to the same categories are aligned together and the confusable categories are separated. By measuring the align complexity of each category, we design an Adaptive-weighted Instance Matching (AIM) strategy to further optimize the instance-level adaptation. Based on our proposed methods, we also raise a hierarchical unsupervised domain adaptation framework for cross-domain semantic segmentation task. Through performing the image-level, feature-level, category-level and instance-level alignment, our method achieves a stronger generalization performance of the model from the source domain to the target domain. In two typical cross-domain semantic segmentation tasks, i.e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy. We also build two cross-domain semantic segmentation datasets based on the publicly available data, i.e., remote sensing building segmentation and road segmentation, for domain adaptive segmentation.

cs.CV↗

arXiv2021

MDFM: Multi-Decision Fusing Model for Few-Shot Learning

In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). ii) Meta-test. Apply the trained FEM to the novel data (category is different from base data) to acquire the feature embeddings and recognize them. Although researchers have made remarkable breakthroughs in FSL, there still exists a fundamental problem. Since the trained FEM with base data usually cannot adapt to the novel class flawlessly, the novel data's feature may lead to the distribution shift problem. To address this challenge, we hypothesize that even if most of the decisions based on different FEMs are viewed as weak decisions, which are not available for all classes, they still perform decently in some specific categories. Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model. MDFM is a simple, flexible, non-parametric method that can directly apply to the existing FEMs. Besides, we extend the proposed MDFM to two FSL settings (i.e., supervised and semi-supervised settings). We evaluate the proposed method on five benchmark datasets and achieve significant improvements of 3.4%-7.3% compared with state-of-the-arts.

cs.CV↗

arXiv2021

SSDL: Self-Supervised Dictionary Learning

The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the label-embedded DL methods rely on the labels due that this way merely achieves ideal performances in supervised learning. While in semi-supervised and unsupervised learning, it is no longer sufficient to be effective. Inspired by the concept of self-supervised learning (e.g., setting the pretext task to generate a universal model for the downstream task), we propose a Self-Supervised Dictionary Learning (SSDL) framework to address this challenge. Specifically, we first design a $p$-Laplacian Attention Hypergraph Learning (pAHL) block as the pretext task to generate pseudo soft labels for DL. Then, we adopt the pseudo labels to train a dictionary from a primary label-embedded DL method. We evaluate our SSDL on two human activity recognition datasets. The comparison results with other state-of-the-art methods have demonstrated the efficiency of SSDL.

cs.LG↗

arXiv2021

MHFC: Multi-Head Feature Collaboration for Few-Shot Learning

Few-shot learning (FSL) aims to address the data-scarce problem. A standard FSL framework is composed of two components: (1) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). (2) Meta-test. Apply the trained FEM to acquire the novel data's features and recognize them. FSL relies heavily on the design of the FEM. However, various FEMs have distinct emphases. For example, several may focus more attention on the contour information, whereas others may lay particular emphasis on the texture information. The single-head feature is only a one-sided representation of the sample. Besides the negative influence of cross-domain (e.g., the trained FEM can not adapt to the novel class flawlessly), the distribution of novel data may have a certain degree of deviation compared with the ground truth distribution, which is dubbed as distribution-shift-problem (DSP). To address the DSP, we propose Multi-Head Feature Collaboration (MHFC) algorithm, which attempts to project the multi-head features (e.g., multiple features extracted from a variety of FEMs) to a unified space and fuse them to capture more discriminative information. Typically, first, we introduce a subspace learning method to transform the multi-head features to aligned low-dimensional representations. It corrects the DSP via learning the feature with more powerful discrimination and overcomes the problem of inconsistent measurement scales from different head features. Then, we design an attention block to update combination weights for each head feature automatically. It comprehensively considers the contribution of various perspectives and further improves the discrimination of features. We evaluate the proposed method on five benchmark datasets (including cross-domain experiments) and achieve significant improvements of 2.1%-7.8% compared with state-of-the-arts.

cs.CV↗

arXiv2021

CIM: Class-Irrelevant Mapping for Few-Shot Classification

Few-shot classification (FSC) is one of the most concerned hot issues in recent years. The general setting consists of two phases: (1) Pre-train a feature extraction model (FEM) with base data (has large amounts of labeled samples). (2) Use the FEM to extract the features of novel data (with few labeled samples and totally different categories from base data), then classify them with the to-be-designed classifier. The adaptability of pre-trained FEM to novel data determines the accuracy of novel features, thereby affecting the final classification performances. To this end, how to appraise the pre-trained FEM is the most crucial focus in the FSC community. It sounds like traditional Class Activate Mapping (CAM) based methods can achieve this by overlaying weighted feature maps. However, due to the particularity of FSC (e.g., there is no backpropagation when using the pre-trained FEM to extract novel features), we cannot activate the feature map with the novel classes. To address this challenge, we propose a simple, flexible method, dubbed as Class-Irrelevant Mapping (CIM). Specifically, first, we introduce dictionary learning theory and view the channels of the feature map as the bases in a dictionary. Then we utilize the feature map to fit the feature vector of an image to achieve the corresponding channel weights. Finally, we overlap the weighted feature map for visualization to appraise the ability of pre-trained FEM on novel data. For fair use of CIM in evaluating different models, we propose a new measurement index, called Feature Localization Accuracy (FLA). In experiments, we first compare our CIM with CAM in regular tasks and achieve outstanding performances. Next, we use our CIM to appraise several classical FSC frameworks without considering the classification results and discuss them.

cs.CV↗

arXiv2021

Hybrid integrated low noise linearly chirped Frequency Modulated Continuous Wave laser source based on self-injection to external cavity

A low noise linearly frequency modulated continuous wave laser source with a wide frequency bandwidth is demonstrated. By two-dimensional thermal tuning, the laser source shows 42 GHz continuous frequency tuning with 49.86 Hz intrinsic linewidth under static operation. For dynamical FMCW, the laser source has 10.25 GHz frequency bandwidth at 100 Hz chirped frequency and 5.56 GHz at 1 kHz chirped frequency. With pre-distortion linearization, it can distinguish 3 m length difference at 45 km distance in the fibre length measured experiment, which demonstrate a potential for application in ultra-long fibre sensing and FMCW LiDAR.

physics.optics↗

arXiv2021

New Planar P-time Computable Six-Vertex Models and a Complete Complexity Classification

We discover new P-time computable six-vertex models on planar graphs beyond Kasteleyn's algorithm for counting planar perfect matchings. We further prove that there are no more: Together, they exhaust all P-time computable six-vertex models on planar graphs, assuming #P is not P. This leads to the following exact complexity classification: For every parameter setting in ${\mathbb C}$ for the six-vertex model, the partition function is either (1) computable in P-time for every graph, or (2) #P-hard for general graphs but computable in P-time for planar graphs, or (3) #P-hard even for planar graphs. The classification has an explicit criterion. The new P-time cases in (2) provably cannot be subsumed by Kasteleyn's algorithm. They are obtained by a non-local connection to #CSP, defined in terms of a "loop space". This is the first substantive advance toward a planar Holant classification with not necessarily symmetric constraints. We introduce Möbius transformation on ${\mathbb C}$ as a powerful new tool in hardness proofs for counting problems.

cs.CC↗

arXiv2020

A Predictive Discrete-Continuum Multiscale Model of Plasticity With Quantified Uncertainty

Multiscale models of materials, consisting of upscaling discrete simulations to continuum models, are unique in their capability to simulate complex materials behavior. The fundamental limitation in multiscale models is the presence of uncertainty in the computational predictions delivered by them. In this work, a sequential multiscale model has been developed, incorporating discrete dislocation dynamics (DDD) simulations and a strain gradient plasticity (SGP) model to predict the size effect in plastic deformations of metallic micro-pillars. The DDD simulations include uniaxial compression of micro-pillars with different sizes and over a wide range of initial dislocation densities and spatial distributions of dislocations. An SGP model is employed at the continuum level that accounts for the size-dependency of flow stress and hardening rate. Sequences of uncertainty analyses have been performed to assess the predictive capability of the multiscale model. The variance-based global sensitivity analysis determines the effect of parameter uncertainty on the SGP model prediction. The multiscale model is then constructed by calibrating the continuum model using the data furnished by the DDD simulations. A Bayesian calibration method is implemented to quantify the uncertainty due to microstructural randomness in discrete dislocation simulations (density and spatial distributions of dislocations) on the macroscopic continuum model prediction (size effect in plastic deformation). The outcomes of this study indicate that the discrete-continuum multiscale model can accurately simulate the plastic deformation of micro-pillars, despite the significant uncertainty in the DDD results. Additionally, depending on the macroscopic features represented by the DDD simulations, the SGP model can reliably predict the size effect in plasticity responses of the micropillars with below 10% of error

cs.CE↗

arXiv2020

SAHDL: Sparse Attention Hypergraph Regularized Dictionary Learning

In recent years, the attention mechanism contributes significantly to hypergraph based neural networks. However, these methods update the attention weights with the network propagating. That is to say, this type of attention mechanism is only suitable for deep learning-based methods while not applicable to the traditional machine learning approaches. In this paper, we propose a hypergraph based sparse attention mechanism to tackle this issue and embed it into dictionary learning. More specifically, we first construct a sparse attention hypergraph, asset attention weights to samples by employing the $\ell_1$-norm sparse regularization to mine the high-order relationship among sample features. Then, we introduce the hypergraph Laplacian operator to preserve the local structure for subspace transformation in dictionary learning. Besides, we incorporate the discriminative information into the hypergraph as the guidance to aggregate samples. Unlike previous works, our method updates attention weights independently, does not rely on the deep network. We demonstrate the efficacy of our approach on four benchmark datasets.

cs.CV↗

arXiv2020

DLDL: Dynamic Label Dictionary Learning via Hypergraph Regularization

For classification tasks, dictionary learning based methods have attracted lots of attention in recent years. One popular way to achieve this purpose is to introduce label information to generate a discriminative dictionary to represent samples. However, compared with traditional dictionary learning, this category of methods only achieves significant improvements in supervised learning, and has little positive influence on semi-supervised or unsupervised learning. To tackle this issue, we propose a Dynamic Label Dictionary Learning (DLDL) algorithm to generate the soft label matrix for unlabeled data. Specifically, we employ hypergraph manifold regularization to keep the relations among original data, transformed data, and soft labels consistent. We demonstrate the efficiency of the proposed DLDL approach on two remote sensing datasets.

cs.CV↗

arXiv2020

Class specific or shared? A cascaded dictionary learning framework for image classification

Dictionary learning methods can be split into: i) class specific dictionary learning ii) class shared dictionary learning. The difference between the two categories is how to use discriminative information. With the first category, samples of different classes are mapped into different subspaces, which leads to some redundancy with the class specific base vectors. While for the second category, the samples in each specific class can not be described accurately. In this paper, we first propose a novel class shared dictionary learning method named label embedded dictionary learning (LEDL). It is the improvement based on LCKSVD, which is easier to find out the optimal solution. Then we propose a novel framework named cascaded dictionary learning framework (CDLF) to combine the specific dictionary learning with shared dictionary learning to describe the feature to boost the performance of classification sufficiently. Extensive experimental results on six benchmark datasets illustrate that our methods are capable of achieving superior performance compared to several state-of-art classification algorithms.

cs.CV↗

arXiv2020

Beyond #CSP: A Dichotomy for Counting Weighted Eulerian Orientations with ARS

We define and explore a notion of unique prime factorization for constraint functions, and use this as a new tool to prove a complexity classification for counting weighted Eulerian orientation problems with arrow reversal symmetry (ARS). We prove that all such problems are either polynomial-time computable or #P-hard. We show that the class of weighted Eulerian orientation problems subsumes all weighted counting constraint satisfaction problems (#CSP) on Boolean variables. More significantly, we establish a novel connection between #CSP and counting weighted Eulerian orientation problems that is global in nature. This connection is based on a structural determination of all half-weighted affine linear subspaces over $\mathbb{Z}_2$, which is proved using Möbius inversion.

cs.CC↗

arXiv2020

A Dichotomy for Real Boolean Holant Problems

We prove a complexity dichotomy for Holant problems on the boolean domain with arbitrary sets of real-valued constraint functions. These constraint functions need not be symmetric nor do we assume any auxiliary functions as in previous results. It is proved that for every set $\mathcal{F}$ of real-valued constraint functions, Holant$(\mathcal{F})$ is either P-time computable or #P-hard. The classification has an explicit criterion. This is the culmination of much research on this problem, and it uses previous results and techniques from many researchers. Some particularly intriguing concrete functions $f_6$, $f_8$ and their associated families with extraordinary closure properties related to Bell states in quantum information theory play an important role in this proof.

cs.CC↗

arXiv2020

From Holant to Quantum Entanglement and Back

Holant problems are intimately connected with quantum theory as tensor networks. We first use techniques from Holant theory to derive new and improved results for quantum entanglement theory. We discover two particular entangled states $|{Ψ_6}\rangle$ of 6 qubits and $|{Ψ_8}\rangle$ of 8 qubits respectively, that have extraordinary and unique closure properties in terms of the Bell property. Then we use entanglement properties of constraint functions to derive a new complexity dichotomy for all real-valued Holant problems containing an odd-arity signature. The signatures need not be symmetric, and no auxiliary signatures are assumed.

cs.CC↗