arXiv subjects

Xiaoqi Wang

Publications and source records attributed to Xiaoqi Wang.

32 records · Page 2Linked to original sources

arXiv2024

USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation

The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recent vision-based foundation models such as the Segment Anything Model (SAM) have shown superior performance in generating class-agnostic image segments. The main challenge in open-vocabulary image segmentation now lies in accurately classifying these segments into text-defined categories. In this paper, we introduce the Universal Segment Embedding (USE) framework to address this challenge. This framework is comprised of two key components: 1) a data pipeline designed to efficiently curate a large amount of segment-text pairs at various granularities, and 2) a universal segment embedding model that enables precise segment classification into a vast range of text-defined categories. The USE model can not only help open-vocabulary image segmentation but also facilitate other downstream tasks (e.g., querying and ranking). Through comprehensive experimental studies on semantic segmentation and part segmentation benchmarks, we demonstrate that the USE framework outperforms state-of-the-art open-vocabulary segmentation methods.

cs.CV↗

arXiv2024

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks

Recently, Graph Neural Networks (GNNs) have significantly advanced the performance of machine learning tasks on graphs. However, this technological breakthrough makes people wonder: how does a GNN make such decisions, and can we trust its prediction with high confidence? When it comes to some critical fields, such as biomedicine, where making wrong decisions can have severe consequences, it is crucial to interpret the inner working mechanisms of GNNs before applying them. In this paper, we propose a model-agnostic model-level explanation method for different GNNs that follow the message passing scheme, GNNInterpreter, to explain the high-level decision-making process of the GNN model. More specifically, GNNInterpreter learns a probabilistic generative graph distribution that produces the most discriminative graph pattern the GNN tries to detect when making a certain prediction by optimizing a novel objective function specifically designed for the model-level explanation for GNNs. Compared to existing works, GNNInterpreter is more flexible and computationally efficient in generating explanation graphs with different types of node and edge features, without introducing another blackbox or requiring manually specified domain-specific rules. In addition, the experimental studies conducted on four different datasets demonstrate that the explanation graphs generated by GNNInterpreter match the desired graph pattern if the model is ideal; otherwise, potential model pitfalls can be revealed by the explanation. The official implementation can be found at https://github.com/yolandalalala/GNNInterpreter.

cs.LG↗

arXiv2023

Regression-free Blind Image Quality Assessment with Content-Distortion Consistency

The optimization objective of regression-based blind image quality assessment (IQA) models is to minimize the mean prediction error across the training dataset, which can lead to biased parameter estimation due to potential training data biases. To mitigate this issue, we propose a regression-free framework for image quality evaluation, which is based upon retrieving locally similar instances by incorporating semantic and distortion feature spaces. The approach is motivated by the observation that the human visual system (HVS) exhibits analogous perceptual responses to semantically similar image contents impaired by identical distortions, which we term as content-distortion consistency. The proposed method constructs a hierarchical k-nearest neighbor (k-NN) algorithm for instance retrieval through two classification modules: semantic classification (SC) module and distortion classification (DC) module. Given a test image and an IQA database, the SC module retrieves multiple pristine images semantically similar to the test image. The DC module then retrieves instances based on distortion similarity from the distorted images that correspond to each retrieved pristine image. Finally, quality prediction is obtained by aggregating the subjective scores of the retrieved instances. Without training on subjective quality scores, the proposed regression-free method achieves competitive, even superior performance compared to state-of-the-art regression-based methods on authentic and synthetic distortion IQA benchmarks.

cs.CV↗

arXiv2023

SmartGD: A GAN-Based Graph Drawing Framework for Diverse Aesthetic Goals

While a multitude of studies have been conducted on graph drawing, many existing methods only focus on optimizing a single aesthetic aspect of graph layouts, which can lead to sub-optimal results. There are a few existing methods that have attempted to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria. Furthermore, thanks to the significant advance in deep learning techniques, several deep learning-based layout methods were proposed recently. These methods have demonstrated the advantages of deep learning approaches for graph drawing. However, none of these existing methods can be directly applied to optimizing non-differentiable criteria without special accommodation. In this work, we propose a novel Generative Adversarial Network (GAN) based deep learning framework for graph drawing, called SmartGD, which can optimize different quantitative aesthetic goals, regardless of their differentiability. To demonstrate the effectiveness and efficiency of SmartGD, we conducted experiments on minimizing stress, minimizing edge crossing, maximizing crossing angle, maximizing shape-based metrics, and a combination of multiple aesthetics. Compared with several popular graph drawing algorithms, the experimental results show that SmartGD achieves good performance both quantitatively and qualitatively.

cs.LG↗

arXiv2022

Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery

Self-supervised representation learning (SSL) on biomedical networks provides new opportunities for drug discovery. However, how to effectively combine multiple SSL models is still challenging and has been rarely explored. Therefore, we propose multi-task joint strategies of self-supervised representation learning on biomedical networks for drug discovery, named MSSL2drug. We design six basic SSL tasks inspired by various modality features including structures, semantics, and attributes in heterogeneous biomedical networks. Importantly, fifteen combinations of multiple tasks are evaluated by a graph attention-based multi-task adversarial learning framework in two drug discovery scenarios. The results suggest two important findings. (1) Combinations of multimodal tasks achieve the best performance compared to other multi-task joint models. (2) The local-global combination models yield higher performance than random two-task combinations when there are the same size of modalities. Therefore, we conjecture that the multimodal and local-global combination strategies can be treated as the guideline of multi-task SSL for drug discovery.

cs.LG↗

arXiv2022

PrEF: Percolation-based Evolutionary Framework for the diffusion-source-localization problem in large networks

We assume that the state of a number of nodes in a network could be investigated if necessary, and study what configuration of those nodes could facilitate a better solution for the diffusion-source-localization (DSL) problem. In particular, we formulate a candidate set which contains the diffusion source for sure, and propose the method, Percolation-based Evolutionary Framework (PrEF), to minimize such set. Hence one could further conduct more intensive investigation on only a few nodes to target the source. To achieve that, we first demonstrate that there are some similarities between the DSL problem and the network immunization problem. We find that the minimization of the candidate set is equivalent to the minimization of the order parameter if we view the observer set as the removal node set. Hence, PrEF is developed based on the network percolation and evolutionary algorithm. The effectiveness of the proposed method is validated on both model and empirical networks in regard to varied circumstances. Our results show that the developed approach could achieve a much smaller candidate set compared to the state of the art in almost all cases. Meanwhile, our approach is also more stable, i.e., it has similar performance irrespective of varied infection probabilities, diffusion models, and outbreak ranges. More importantly, our approach might provide a new framework to tackle the DSL problem in extreme large networks.

cs.SI↗

arXiv2022

FEDI: Few-shot learning based on Earth Mover's Distance algorithm combined with deep residual network to identify diabetic retinopathy

Diabetic retinopathy(DR) is the main cause of blindness in diabetic patients. However, DR can easily delay the occurrence of blindness through the diagnosis of the fundus. In view of the reality, it is difficult to collect a large amount of diabetic retina data in clinical practice. This paper proposes a few-shot learning model of a deep residual network based on Earth Mover's Distance algorithm to assist in diagnosing DR. We build training and validation classification tasks for few-shot learning based on 39 categories of 1000 sample data, train deep residual networks, and obtain experience maximization pre-training models. Based on the weights of the pre-trained model, the Earth Mover's Distance algorithm calculates the distance between the images, obtains the similarity between the images, and changes the model's parameters to improve the accuracy of the training model. Finally, the experimental construction of the small sample classification task of the test set to optimize the model further, and finally, an accuracy of 93.5667% on the 3way10shot task of the diabetic retina test set. For the experimental code and results, please refer to: https://github.com/panliangrui/few-shot-learning-funds.

eess.IV↗

arXiv2021

DeepGD: A Deep Learning Framework for Graph Drawing Using GNN

In the past decades, many graph drawing techniques have been proposed for generating aesthetically pleasing graph layouts. However, it remains a challenging task since different layout methods tend to highlight different characteristics of the graphs. Recently, studies on deep learning based graph drawing algorithm have emerged but they are often not generalizable to arbitrary graphs without re-training. In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained. It attempts to generate layouts by compromising among multiple pre-specified aesthetics considering a good graph layout usually complies with multiple aesthetics simultaneously. In order to balance the trade-off, we propose two adaptive training strategies which adjust the weight factor of each aesthetic dynamically during training. The quantitative and qualitative assessment of DeepGD demonstrates that it is capable of drawing arbitrary graphs effectively, while being flexible at accommodating different aesthetic criteria.

cs.LG↗

arXiv2020

Secrecy Performance of Body-Centric Communications over Alternate Rician Shadowed Fading Channels

In this paper, we investigate the physical layer security over the Alternate Rician Shadowed fading channel, which is a novel channel model for body-centric wireless links and land mobile satellite. We derive exact closed-form expressions for the average secrecy capacity (ASC), secrecy outage probability (SOP), and probability of non-zero secrecy capacity (PNZ) for two cases: (i) m is a positive real number and (ii) m is a positive integer number, where m describes the level of fluctuation of the line-of-sight component. In the first case, SOP is derived in terms of the Meijer's G-function, while ASC and PNZ are derived in terms of the multivariate Fox's H-function. In the second case, ASC is derived in terms of the Meijer's G-function, while SOP and PNZ are derived in terms of elementary functions. In addition, we derive the asymptotic ASC, SOP and PNZ expressions which all match well the exact ones at high values of signal-to-noise ratio, respectively. The capacity slope of asymptotic ASC and the secrecy diversity order of asymptotic SOP have been derived for providing more physical insights. Finally, the accuracy of our derived expressions is validated by Monte-Carlo simulations.

cs.IT↗

arXiv2018

Insights into End-to-End Learning Scheme for Language Identification

A novel interpretable end-to-end learning scheme for language identification is proposed. It is in line with the classical GMM i-vector methods both theoretically and practically. In the end-to-end pipeline, a general encoding layer is employed on top of the front-end CNN, so that it can encode the variable-length input sequence into an utterance level vector automatically. After comparing with the state-of-the-art GMM i-vector methods, we give insights into CNN, and reveal its role and effect in the whole pipeline. We further introduce a general encoding layer, illustrating the reason why they might be appropriate for language identification. We elaborate on several typical encoding layers, including a temporal average pooling layer, a recurrent encoding layer and a novel learnable dictionary encoding layer. We conducted experiment on NIST LRE07 closed-set task, and the results show that our proposed end-to-end systems achieve state-of-the-art performance.

eess.AS↗

arXiv2018

A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of traditional GMM training and Supervector encoding procedure on the top of CNN. The proposed layer can accumulate high-order statistics from variable-length input sequence and generate an utterance level fixed-dimensional vector representation. Unlike the conventional methods, our new approach provides an end-to-end learning framework, where the inherent dictionary are learned directly from the loss function. The dictionaries and the encoding representation for the classifier are learned jointly. The representation is orderless and therefore appropriate for language identification. We conducted a preliminary experiment on NIST LRE07 closed-set task, and the results reveal that our proposed dictionary encoding layer achieves significant error reduction comparing with the simple average pooling.

eess.AS↗

arXiv2012

Resistance Switching Induced by Electric Field and Light Illumination in Device of FTO/CeO2/Electrolyte/FTO

A heterojunction-like device consisting of FTO/CeO2/electrolyte/FTO is established with distinct transport performance, where FTO denotes F-doped transparent conducting glass, and the electrolyte is LiI and I2 in acetonitrile. The resistive switching behavior is observed, being induced through applying sufficient negative pulse as well as light illumination. The endurance measurements confirm that the write/erase periodic operation is reproducible and stable in the present device. Furthermore, the retention measurements demonstrate that the information can be stored temporarily for about 100 seconds. A possible mechanism regarding the formation of diiodide radical is proposed to give a reasonable explanation for the observed switching behavior.

physics.chem-ph↗

arXiv2012

Study of band bending effect in Dye Sensitized Solar Cell through Constant-Current-Discharging Voltage Decay

A measurement method of constant-current-discharging voltage decay is established to characterize the band bending effect in the heterojunction of conducting glass/TiO2 for typical dye-sensitized solar cells. Furthermore, a dark-state electron transport regarding the TiO2 conduction band bending is proposed based upon the viewpoints of thermionic emission mechanism, which suggests an origin of the band bending effect in a theoretical model. This model quantitatively agrees well with our experimental results and indicates that both the Fermi level decay in TiO2 and the potential difference across the heterojunction will lead to the TiO2 conduction band bending downwards.

physics.chem-ph↗

arXiv2012

Low-voltage Driving Phototransistor Based on Dye-sensitized Nanocrystalline Titanium Dioxide Thin Films

Photo-gated transistors based on dye-sensitized nanocrystalline titanium dioxide thin film are established. A transistor-like transport behavior characterized by the linear increase, saturated plateau, and breakdown-like increase in the voltage-current curve is achievable with a low driven bias for the present device. The response current exhibits a linear dependence on the intensity of gated light, and the measured maximum photosensitivity is approximately 0.1 A/W. The dynamic responses for various light frequencies and their dependences on the load resistances are investigated as well. The cut-off frequency of ~50 Hz is abstracted, indicating the potential application for economical and efficient light switch or optical communication unit. The dc photo-gated response is explained by the energy level diagram, and is numerically simulated by an equivalent circuit model, suggesting a clear correlation between photovoltaic and photoconductive behaviors as well as their optical responses.

physics.chem-ph↗