arXiv subjects

Bingyu Li

Publications and source records attributed to Bingyu Li.

28 records · Page 2Linked to original sources

arXiv2024

Boosting the Targeted Transferability of Adversarial Examples via Salient Region & Weighted Feature Drop

Deep neural networks can be vulnerable to adversarially crafted examples, presenting significant risks to practical applications. A prevalent approach for adversarial attacks relies on the transferability of adversarial examples, which are generated from a substitute model and leveraged to attack unknown black-box models. Despite various proposals aimed at improving transferability, the success of these attacks in targeted black-box scenarios is often hindered by the tendency for adversarial examples to overfit to the surrogate models. In this paper, we introduce a novel framework based on Salient region & Weighted Feature Drop (SWFD) designed to enhance the targeted transferability of adversarial examples. Drawing from the observation that examples with higher transferability exhibit smoother distributions in the deep-layer outputs, we propose the weighted feature drop mechanism to modulate activation values according to weights scaled by norm distribution, effectively addressing the overfitting issue when generating adversarial examples. Additionally, by leveraging salient region within the image to construct auxiliary images, our method enables the adversarial example's features to be transferred to the target category in a model-agnostic manner, thereby enhancing the transferability. Comprehensive experiments confirm that our approach outperforms state-of-the-art methods across diverse configurations. On average, the proposed SWFD raises the attack success rate for normally trained models and robust models by 16.31% and 7.06% respectively.

cs.IR↗

arXiv2024

Quantum-inspired Interpretable Deep Learning Architecture for Text Sentiment Analysis

Text has become the predominant form of communication on social media, embedding a wealth of emotional nuances. Consequently, the extraction of emotional information from text is of paramount importance. Despite previous research making some progress, existing text sentiment analysis models still face challenges in integrating diverse semantic information and lack interpretability. To address these issues, we propose a quantum-inspired deep learning architecture that combines fundamental principles of quantum mechanics (QM principles) with deep learning models for text sentiment analysis. Specifically, we analyze the commonalities between text representation and QM principles to design a quantum-inspired text representation method and further develop a quantum-inspired text embedding layer. Additionally, we design a feature extraction layer based on long short-term memory (LSTM) networks and self-attention mechanisms (SAMs). Finally, we calculate the text density matrix using the quantum complex numbers principle and apply 2D-convolution neural networks (CNNs) for feature condensation and dimensionality reduction. Through a series of visualization, comparative, and ablation experiments, we demonstrate that our model not only shows significant advantages in accuracy and efficiency compared to previous related models but also achieves a certain level of interpretability by integrating QM principles. Our code is available at QISA.

cs.CV↗

arXiv2024

CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning

Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in identifying class-specific visual features, thus facilitating visual-semantic alignment and improving ZSL performance. However, real-world challenges such as distribution imbalances and attribute co-occurrence among instances often hinder the discernment of local variances in images, a problem exacerbated by the scarcity of fine-grained, region-specific attribute annotations. Moreover, the variability in visual presentation within categories can also skew attribute-category associations. In response, we propose a bidirectional cross-modal ZSL approach CREST. It begins by extracting representations for attribute and visual localization and employs Evidential Deep Learning (EDL) to measure underlying epistemic uncertainty, thereby enhancing the model's resilience against hard negatives. CREST incorporates dual learning pathways, focusing on both visual-category and attribute-category alignments, to ensure robust correlation between latent and observable spaces. Moreover, we introduce an uncertainty-informed cross-modal fusion technique to refine visual-attribute inference. Extensive experiments demonstrate our model's effectiveness and unique explainability across multiple datasets. Our code and data are available at: https://github.com/JethroJames/CREST

cs.CV↗

arXiv2024

U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation

Multimodal semantic segmentation is a pivotal component of computer vision and typically surpasses unimodal methods by utilizing rich information set from various sources.Current models frequently adopt modality-specific frameworks that inherently biases toward certain modalities. Although these biases might be advantageous in specific situations, they generally limit the adaptability of the models across different multimodal contexts, thereby potentially impairing performance. To address this issue, we leverage the inherent capabilities of the model itself to discover the optimal equilibrium in multimodal fusion and introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation. Specifically, this method involves an unbiased integration of multimodal visual data. Additionally, we employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets, verifing its efficacy in enhancing the robustness and versatility of semantic segmentation in diverse settings. Our code is available at U3M-multimodal-semantic-segmentation.

cs.CV↗

arXiv2016

Generalized Mountain Pass Lemma Related with a Closed Subset and Locally Lipschitz Functionals

The classical Mountain Pass Lemma of Ambrosetti-Rabinowitz has been studied, extended and modified in several directions, notable examples would certainly include the generalization to locally Lipschitz functionals in K.C. Chang, analysis of the structure of the critical set in the mountain pass theorem by Hofer and Pucci-Serrin and Tian, the extension by Ghoussoub-Preiss to closed subsets in a Banach space, and variations found in the recent Peral . In this paper, we utilize the generalized gradient of Clarke and Ekeland's variational principle to generalize the Ghoussoub-Preiss's Theorem in the setting of locally Lipschitz functionals.

math.FA↗

arXiv2016

Four-body Central Configurations with Adjacent Equal Masses

For any convex non-collinear central configuration of the planar Newtonian 4-body problem with adjacent equal masses $m_1=m_2\neq m_3=m_4$, with equal lengths for the two diagonals, we prove it must possess a symmetry and must be an isosceles trapezoid; furthermore, which is also an isosceles trapezoid when the length between $m_1$ and $ m_4$ equals the length between $m_2$ and $ m_3$.

math.DS↗

arXiv2015

On the Condition Number of the Total Least Squares Problem

This paper concerns singular value decomposition (SVD)-based computable formulas and bounds for the condition number of the Total Least Squares (TLS) problem. For the TLS problem with the coefficient matrix $A$ and the right-hand side $b$, a new closed formula is presented for the condition number. Unlike an important result in the literature that uses the SVDs of both $A$ and $[A,\ b]$, our formula only requires the SVD of $[A,\ b]$. Based on the closed formula, both lower and upper bounds for the condition number are derived. It is proved that they are always sharp and estimate the condition number accurately. A few lower and upper bounds are further established that involve at most the smallest two singular values of $A$ and of $[A,\ b]$. Tightness of these bounds is discussed, and numerical experiments are presented to confirm our theory and to demonstrate the improvement of our upper bounds over the two upper bounds due to Golub and Van Loan as well as Baboulin and Gratton. Such lower and upper bounds are particularly useful for large scale TLS problems since they require the computation of only a few singular values of $A$ and $[A, \ b]$ other than all the singular values of them.

math.NA↗

arXiv2014

A Note on Homoclinic Orbits for Second Order Hamiltonian Systems

In this paper, we study the existence for the homoclinic orbits for the second order Hamiltonian systems. Under suitable conditions on the potential $V$, we apply the direct method of variations and the Fourier analysis to prove the existence of homoclinc orbits.

math.DS↗

arXiv2014

Some Applications of Generalized Mountain Pass Lemma

The Ghoussoub-Preiss's generalized Mountain Pass Lemma with Cerami-Palais-Smale type condition is a generalization of classical MPL of Ambrosetti-Rabinowitz, we apply it to study the existence of the periodic solutions with a given energy for some second order Hamiltonian systems with symmetrical and non-symmetrical potentials.

math.FA↗

arXiv2011

A contribution to the condition number of the total least squares problem

This paper concerns cheaply computable formulas and bounds for the condition number of the TLS problem. For a TLS problem with data $A$, $b$, two formulas are derived that are simpler and more compact than the known results in the literature. One is derived by exploiting the properties of Kronecker products of matrices. The other is obtained by making use of the singular value decomposition (SVD) of $[A \,\,b]$, which allows us to compute the condition number cheaply and accurately. We present lower and upper bounds for the condition number that involve the singular values of $[A \,\, b]$ and the last entries of the right singular vectors of $[A \,\, b]$. We prove that they are always sharp and can estimate the condition number accurately by no more than four times. Furthermore, we establish a few other lower and upper bounds that involve only a few singular values of $A$ and $[A \,\, b]$. We discuss how tight the bounds are. These bounds are particularly useful for large scale TLS problems since for them any formulas and bounds for the condition number involving all the singular values of $A$ and/or $[A \ b]$ are too costly to be computed. Numerical experiments illustrate that our bounds are sharper than a known approximate condition number in the literature.

math.NA↗