40 citations · 94 across the 30 of their papers we have counts for
34 papers
Subspace Learning with Outlier Exposure for Out-of-Distribution Detection
Hongxu Shen, Kun Fang, Jiahui Zheng +2
Out-of-Distribution (OoD) detection is pivotal for reliable deployments of Deep Neural Networks (DNNs), aiming to distinguish anomalous samples from the In-Distribution (InD) data…
Kernel Singular Value Decomposition with Extension to Multiple Data Sources
Xinjie Zeng, Qinghua Tao, Johan Suykens
Kernel Singular Value Decomposition (KSVD) learns a pair of singular vectors w.r.t. an asymmetric kernel matrix, which can be induced by two data sources, e.g., the queries and key…
Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis
Peilin Yang, Xiaoyu Liu, Jian Sun +1
Vision-language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named KUEA presents a natural remedy…
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
Wei Tao, Yang Dai, Jincai Huang +1
Crafting adversarial examples can be formulated as an optimization problem. While sign-based optimizers such as I-FGSM and MI-FGSM have become the de facto standard for the induced…
Machine Unlearning in Low-Dimensional Feature Subspace
Kun Fang, Qinghua Tao, Junxu Liu +5
Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspectiv…
Optimizing the Adversarial Perturbation with a Momentum-based Adaptive Matrix
Wei Tao, Sheng Long, Xin Liu +2
Generating adversarial examples (AEs) can be formulated as an optimization problem. Among various optimization-based attacks, the gradient-based PGD and the momentum-based MI-FGSM…
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation
Kun Fang, Qinghua Tao, Mingzhen He +6
Out-of-Distribution (OoD) detection is vital for the reliability of deep neural networks, the key of which lies in effectively characterizing the disparities between OoD and In-Dis…
From Dense to Sparse: Event Response for Enhanced Residential Load Forecasting
Xin Cao, Qinghua Tao, Yingjie Zhou +5
Residential load forecasting (RLF) is crucial for resource scheduling in power systems. Most existing methods utilize all given load records (dense data) to indiscriminately extrac…
Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model
Kun Fang, Zuopeng Yang, Haibo Hu +3
Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or fro…
Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
Qinghua Tao, Francesco Tonin, Alex Lambert +3
In contrast with Mercer kernel-based approaches as used e.g., in Kernel Principal Component Analysis (KPCA), it was previously shown that Singular Value Decomposition (SVD) inheren…
Revisiting Random Weight Perturbation for Efficiently Improving Generalization
Tao Li, Qinghua Tao, Weihao Yan +5
Improving the generalization ability of modern deep neural networks (DNNs) is a fundamental challenge in machine learning. Two branches of methods have been proposed to seek flat m…
Sparsity via Sparse Group -max Regularization
Qinghua Tao, Xiangming Xi, Jun Xu +1
For the linear inverse problem with sparsity constraints, the regularized problem is NP-hard, and existing approaches either utilize greedy algorithms to find almost-optimal…
Kernel PCA for Out-of-Distribution Detection
Kun Fang, Qinghua Tao, Kexin Lv +3
Out-of-Distribution (OoD) detection is vital for the reliability of Deep Neural Networks (DNNs). Existing works have shown the insufficiency of Principal Component Analysis (PCA) s…
Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes
Yingyi Chen, Qinghua Tao, Francesco Tonin +1
While the great capability of Transformers significantly boosts prediction accuracy, it could also yield overconfident predictions and require calibrated uncertainty estimation, wh…
Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
Kun Fang, Qinghua Tao, Xiaolin Huang +1
Existing Out-of-Distribution (OoD) detection methods address to detect OoD samples from In-Distribution (InD) data mainly by exploring differences in features, logits and gradients…
Low-Rank Multitask Learning based on Tensorized SVMs and LSSVMs
Jiani Liu, Qinghua Tao, Ce Zhu +3
Multitask learning (MTL) leverages task-relatedness to enhance performance. With the emergence of multimodal data, tasks can now be referenced by multiple indices. In this paper, w…
Nonlinear SVD with Asymmetric Kernels: feature learning and asymmetric Nyström method
Qinghua Tao, Francesco Tonin, Panagiotis Patrinos +1
Asymmetric data naturally exist in real life, such as directed graphs. Different from the common kernel methods requiring Mercer kernels, this paper tackles the asymmetric kernel-b…
Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation
Yingyi Chen, Qinghua Tao, Francesco Tonin +1
Recently, a new line of works has emerged to understand and improve self-attention in Transformers by treating it as a kernel machine. However, existing works apply the methods for…
Tensorized LSSVMs for Multitask Regression
Jiani Liu, Qinghua Tao, Ce Zhu +2
Multitask learning (MTL) can utilize the relatedness between multiple tasks for performance improvement. The advent of multimodal data allows tasks to be referenced by multiple ind…
Deep Kernel Principal Component Analysis for Multi-level Feature Learning
Francesco Tonin, Qinghua Tao, Panagiotis Patrinos +1
Principal Component Analysis (PCA) and its nonlinear extension Kernel PCA (KPCA) are widely used across science and industry for data analysis and dimensionality reduction. Modern…
Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
Kun Fang, Qinghua Tao, Yingwen Wu +3
Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple Deep Neural Networks (DNNs) has shown state-of-the-art perf…
Tensor-based Multi-view Spectral Clustering via Shared Latent Space
Qinghua Tao, Francesco Tonin, Panagiotis Patrinos +1
Multi-view Spectral Clustering (MvSC) attracts increasing attention due to diverse data sources. However, most existing works are prohibited in out-of-sample predictions and overlo…
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer
Yingyi Chen, Xi Shen, Yahui Liu +2
The success of Vision Transformer (ViT) in various computer vision tasks has promoted the ever-increasing prevalence of this convolution-free network. The fact that ViT works on im…
Piecewise Linear Neural Networks and Deep Learning
Qinghua Tao, Li Li, Xiaolin Huang +3
As a powerful modelling method, PieceWise Linear Neural Networks (PWLNNs) have proven successful in various fields, most recently in deep learning. To apply PWLNN methods, both the…