Author name cluster

Honghui Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2026 Conference Paper

TRT: Harnessing Tensor Ring Transformer for Hyperspectral Image Super-Resolution

Honghui Xu
Junwei Zhu
Yubin Gu
Yueqian Quan
Chuangjie Fang
Hong Qiu
Jianwei Zheng

Deep unfolding networks (DUNs) have recently emerged as a promising approach for hyperspectral image super-resolution (HSISR) by combining the benefits of nonlinear deep learning architectures with interpretable optimization techniques. Despite their advantages, current DUNs face significant challenges, particularly in approximating degradation matrices across both spatial and spectral dimensions, which results in complex and cumbersome model construction. By analyzing the difference between the upsampled low-resolution hyperspectral images (LRHS) and the true target image, we observed that the residual image exhibits strong sparsity, akin to noise. Leveraging this insight, we reformulate the HSISR problem as a robust principal component analysis (RPCA)-based denoising task, effectively eliminating the need for the complex approximation of spatial degradation matrix and its transpose. In addition, we introduce a Tensor Ring Transformer based on multilinear products as the prior term, wherein tokens are mapped to a tensor ring factor domain and the traditional dot product is replaced with a multilinear tensor ring product. This significantly reduces the computational complexity of the Transformer model, from \( \mathcal{O}(N^2d) \) to \( \mathcal{O}(Nr^2) \), with \( r<

PDF Details DOI

YNIMG Journal 2025 Journal Article

The modulation of selective attention and divided attention on cross-modal congruence

Honghui Xu
Guochun Yang
Florian Göschl
Qiaoyue Ren
Mei Yu
Qi Li
Xun Liu

Previous studies have demonstrated that performance under selective attention and divided attention can be enhanced or impaired, depending on whether the stimuli from different modalities are the same or different. However, it remains unclear whether the modulation of selective attention and divided attention on cross-modal congruence involves shared or distinct neural mechanisms. To clarify this, the present study adopted an audiovisual Stroop task (measuring selective attention) and an audiovisual Matching task (measuring divided attention), using the same physical stimuli, along with event-related potential (ERP) and time-frequency measures. The behavioral results revealed better performance when the auditory and visual stimuli were the same in both tasks. Electroencephalography (EEG) results revealed that different auditory and visual stimuli elicited increased N2 and late positive component (LPC) amplitudes, as well as increased theta power, in both tasks. Moreover, in the audiovisual Matching task, the P3 amplitude was lower in the different condition, and the delta power was greater in the same condition. However, in the audiovisual Stroop task, the amplitude of the N450 component was greater, and beta power was lower, in the different condition. These results indicate that both shared and distinct neural mechanisms underlie the modulation of different types of attention on cross-modal congruence.

Details DOI

AAAI Conference 2024 Conference Paper

SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting

Jie Wu
Yuchao Feng
Honghui Xu
Chuanmeng Zhu
Jianwei Zheng

Image inpainting is in full bloom accompanied by the progress of convolutional neural networks (CNNs) and transformers, revolutionizing the practical management of abnormity disposal, image editing, etc. However, due to the ever-mounting image resolutions and missing areas, the challenges of distorted long-range dependencies from cluttered background distributions and reduced reference information in image domain inevitably rise, which further cause severe performance degradation. To address the challenges, we propose a novel large-portion image inpainting approach, namely the Structure-Guided Synergism Transformer (SyFormer), to rectify the discrepancies in feature representation and enrich the structural cues from limited reference. Specifically, we devise a dual-routing filtering module that employs a progressive filtering strategy to eliminate invalid noise interference and establish global-level texture correlations. Simultaneously, the structurally compact perception module maps an affinity matrix within the introduced structural priors from a structure-aware generator, assisting in matching and filling the corresponding patches of large-proportionally damaged images. Moreover, we carefully assemble the aforementioned modules to achieve feature complementarity. Finally, a feature decoding alignment scheme is introduced in the decoding process, which meticulously achieves texture amalgamation across hierarchical features. Extensive experiments are conducted on two publicly available datasets, i.e., CelebA-HQ and Places2, to qualitatively and quantitatively demonstrate the superiority of our model over state-of-the-arts.

PDF Details DOI

TCS Journal 2023 Journal Article

Analysis on methods to effectively improve transfer learning performance

Honghui Xu
Wei Li
Zhipeng Cai

Transfer learning has become a prevailing machine learning technique thanks to its superiority in learning knowledge from limited training data for prediction. In the existing works, collection and collaboration are two major approaches to realize the improvement of transfer learning performance. Even though the effectiveness of these approaches has been validated in extensive experiments, there lacks the support of theoretical analysis. Consequently, how to enhance transfer learning effectively is an open problem. In light of this, in this paper, we thoroughly and deeply study the methods of improving transfer learning performance in order to provide the guidelines for applying transfer learning in real applications. Through our proof process, critical conclusions are drawn to help learn the motivation of implementing collection and collaboration, the performance gap between collection and collaboration, and the impacts of data sharing strategies on transfer learning in collaboration. These conclusions can further build a theoretical foundation for future research on transfer learning.

Details DOI

EAAI Journal 2021 Journal Article

Tensor completion using patch-wise high order Hankelization and randomized tensor ring initialization

Jianwei Zheng
Mengjie Qin
Honghui Xu
Yuchao Feng
Peijun Chen
Shengyong Chen

Recently, tensor completion (TC), namely high-order extension of matrix completion, has aroused widespread attention. Many priors have been investigated turning the ill-posed TC problem into a well-posed one. The typical methods, however, either perform suboptimally due to missing consideration of appropriate priors, or suffer from overly complicated models by combining too many constraints. In this study, we go deeper by providing a detailed analysis on the rank properties in patch-wise and Hankel cases, figuring out both these two ingredients ensure stricter low-rank prior. This prompts us to design a resultful yet simple TC method using patch-wise and multi-way tensor extension. Specifically, strict low-rank property can be guaranteed in the formulated tensors and this is achieved without requiring any neighborhood setting. Moreover, to approximate the intrinsic rank of the Hankelized tensor, tensor ring decomposition is introduced after deeply comparing its superiority over other high-order decomposition techniques. The proposed method can be efficiently solved using alternating least squares (ALS) approach. Furthermore, a randomized tensor ring approximation is presented for fast initialization. Experimental results on color image inpainting demonstrate that the proposed method can generate better recovery performance compared with state-of-the-art low-rank related competitors, especially in cases of quite limited known pixels, e. g. , 10%.

Details DOI