Author name cluster

Zhihui Li

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.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models

Longtao Jiang
Jie Huang
Mingfei Han
Lei Chen
Yongqiang Yu
Feng Zhao
Xiaojun Chang
Zhihui Li

Text-guided image inpainting aims to inpaint masked image regions based on a textual prompt while preserving the background. Although diffusion-based methods have become dominant, their property of modeling the entire image in latent space makes it challenging for the results to align well with prompt details and maintain a consistent background. To address these issues, we explore Mask AutoRegressive (MAR) models for this task. MAR naturally supports image inpainting by generating latent tokens corresponding to mask regions, enabling better local controllability without altering the background. However, directly applying MAR to this task makes the inpainting content either ignore the prompts or be disharmonious with the background context. Through analysis of the attention maps from the inpainting images, we identify the impact of background tokens on text tokens during the MAR generation, and leverage this to designToken Painter, a training-free text-guided image inpainting method based on MAR. Our approach introduces two key components: (1) Dual-Stream Encoder Information Fusion (DEIF), which fuses the semantic and context information from text and background in frequency domain to produce novel guidance tokens, allowing MAR to generate text-faithful inpainting content while keeping harmonious with background context. (2) Adaptive Decoder Attention Score Enhancing (ADAE), which adaptively enhances attention scores on guidance tokens and inpainting tokens to further enhance the alignment of prompt details and the content visual quality. Extensive experiments demonstrate that our training-free method outperforms prior state-of-the-art methods across almost all metrics.

PDF Details DOI

EAAI Journal 2025 Journal Article

A lightweight and robust detection network for diverse glass surface defects via scale- and shape-aware feature extraction

Huan Yu
Jin Wang
Jingru Yang
Yiming Liang
Zhihui Li
Zhan Wang
Haiyan He
Xusheng Zhang

As glass usage expands across industries, intelligent glass defect detection is essential for ensuring quality. However, the varying shapes and sizes of defects, coupled with numerous subtle defects and the demand for efficient detection, present challenges for existing methods in achieving both accurate and real-time detection. To address these, we propose the lightweight and robust Glass Surface Defect Network (GSDNet) via scale- and shape-aware feature extraction. Specifically, the novel Shape-aware Feature Extraction (SFE) block, which employs deformable convolution with special linear shape-adaptive offset constraints, forms the feature extraction network, enabling the adaptive extraction of local features for defects with irregular shapes. Meanwhile, the Scale-aware (SA) attention is proposed, incorporating spatial attention mechanism to guide the model in focusing on key features across different receptive fields, enhancing defect detection at various scales. Finally, to enhance detection efficiency, the Efficient Bidirectional Path Aggregation Network (EBiPAN) is proposed as the feature aggregation module, integrating high-resolution information through bi-directional concatenation to improve small defect detection while avoiding significant additional computational burden. To validate the effectiveness of GSDNet, we compile the first multi-class glass defect dataset, covering 4 types of glass and 12 defect categories. Extensive experiments demonstrate GSDNet exhibits exceptional accuracy and robustness, consistently outperforming 9 advanced networks, with a 6. 8% improvement in mean Average Precision and a notable 10. 9% improvement in mean Average Precision small over the You Only Look Once version 8. Moreover, the optimal balance of accuracy and efficiency is achieved, with a detection speed of 68 frames per second. The dataset and code are publicly available at: https: //github. com/FisherYuuri/GSDNet.

Details DOI

JMLR Journal 2023 Journal Article

MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library

Siyi Hu
Yifan Zhong
Minquan Gao
Weixun Wang
Hao Dong
Xiaodan Liang
Zhihui Li
Xiaojun Chang

A significant challenge facing researchers in the area of multi-agent reinforcement learning (MARL) pertains to the identification of a library that can offer fast and compatible development for multi-agent tasks and algorithm combinations, while obviating the need to consider compatibility issues. In this paper, we present MARLlib, a library designed to address the aforementioned challenge by leveraging three key mechanisms: 1) a standardized multi-agent environment wrapper, 2) an agent-level algorithm implementation, and 3) a flexible policy mapping strategy. By utilizing these mechanisms, MARLlib can effectively disentangle the intertwined nature of the multi-agent task and the learning process of the algorithm, with the ability to automatically alter the training strategy based on the current task's attributes. The MARLlib library's source code is publicly accessible on GitHub: https://github.com/Replicable-MARL/MARLlib. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

AAAI Conference 2020 Conference Paper

Adaptive Two-Dimensional Embedded Image Clustering

Zhihui Li
Lina Yao
Sen Wang
Salil Kanhere
Xue Li
Huaxiang Zhang

With the rapid development of mobile devices, people are generating huge volumes of images data every day for sharing on social media, which draws much research attention to understanding the contents of images. Image clustering plays an important role in image understanding systems. Often, most of the existing image clustering algorithms ﬂatten digital images that are originally represented by matrices into 1D vectors as the image representation for the subsequent learning. The drawbacks of vector-based algorithms include limited consideration of spatial relationship between pixels and computational complexity, both of which blame to the simple vectorized representation. To overcome the drawbacks, we propose a novel image clustering framework that can work directly on matrices of images instead of ﬂattened vectors. Speciﬁcally, the proposed algorithm simultaneously learn the clustering results and preserve the original correlation information within the image matrix. To solve the challenging objective function, we propose a fast iterative solution. Extensive experiments have been conducted on various benchmark datasets. The experimental results conﬁrm the superiority of the proposed algorithm.

PDF Details

AAAI Conference 2020 Conference Paper

Robust Self-Weighted Multi-View Projection Clustering

Beilei Wang
Yun Xiao
Zhihui Li
Xuanhong Wang
Xiaojiang Chen
Dingyi Fang

Many real-world applications involve data collected from different views and with high data dimensionality. Furthermore, multi-view data always has unavoidable noise. Clustering on this kind of high-dimensional and noisy multi-view data remains a challenge due to the curse of dimensionality and ineffective de-noising and integration of multiple views. Aiming at this problem, in this paper, we propose a Robust Selfweighted Multi-view Projection Clustering (RSwMPC) based on 2, 1-norm, which can simultaneously reduce dimensionality, suppress noise and learn local structure graph. Then the obtained optimal graph can be directly used for clustering while no further processing is required. In addition, a new method is introduced to automatically learn the optimal weight of each view with no need to generate additional parameters to adjust the weight. Extensive experimental results on different synthetic datasets and real-world datasets demonstrate that the proposed algorithm outperforms other state-ofthe-art methods on clustering performance and robustness.

PDF Details

TIST Journal 2020 Journal Article

Self-weighted Robust LDA for Multiclass Classification with Edge Classes

Caixia Yan
Xiaojun Chang
Minnan Luo
Qinghua Zheng
Xiaoqin Zhang
Zhihui Li
Feiping Nie

Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are prone to be dominated by the class with very large deviation from the others, i.e., edge class, which occurs frequently in multi-class classification. First, the existence of edge classes often makes the total mean biased in the calculation of between-class scatter matrix. Second, the exploitation of ℓ 2 -norm based between-class distance criterion magnifies the extremely large distance corresponding to edge class. In this regard, a novel self-weighted robust LDA with ℓ 2,1 -norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes. SWRLDA can automatically avoid the optimal mean calculation and simultaneously learn adaptive weights for each class pair without setting any additional parameter. An efficient re-weighted algorithm is exploited to derive the global optimum of the challenging ℓ 2,1 -norm maximization problem. The proposed SWRLDA is easy to implement and converges fast in practice. Extensive experiments demonstrate that SWRLDA performs favorably against other compared methods on both synthetic and real-world datasets while presenting superior computational efficiency in comparison with other techniques.

Details DOI

AAAI Conference 2019 Conference Paper

RS3CIS: Robust Single-Step Spectral Clustering with Intrinsic Subspace

Yun Xiao
Pengzhen Ren
Zhihui Li
Xiaojiang Chen
Xin Wang
Dingyi Fang

Spectral clustering has been widely adopted because it can mine structures between data clusters. The clustering performance of spectral clustering depends largely on the quality of the constructed affinity graph, especially when the data has noise. Subspace learning can transform the original input features to a low-dimensional subspace and help to produce a robust method. Therefore, how to learn an intrinsic subspace and construct a pure affinity graph on a dataset with noise is a challenge in spectral clustering. In order to deal with this challenge, a new Robust Single-Step Spectral Clustering with Intrinsic Subspace (RS3 CIS) method is proposed in this paper. RS3 CIS uses a local representation method that projects the original data into a low-dimensional subspace through a row-sparse transformation matrix and uses the `2, 1-norm of the transformation matrix as a penalty term to achieve noise suppression. In addition, RS3 CIS introduces Laplacian matrix rank constraint so that it can output an affinity graph with an explicit clustering structure, which makes the final clustering result to be obtained in a single-step of constructing an affinity matrix. One synthetic dataset and six real benchmark datasets are used to verify the performance of the proposed method by performing clustering and projection experiments. Experimental results show that RS3 CIS outperforms the related methods with respect to clustering quality, robustness and dimension reduction.

PDF Details

AAAI Conference 2019 Conference Paper

Zero-Shot Object Detection with Textual Descriptions

Zhihui Li
Lina Yao
Xiaoqin Zhang
Xianzhi Wang
Salil Kanhere
Huaxiang Zhang

Object detection is important in real-world applications. Existing methods mainly focus on object detection with sufficient labelled training data or zero-shot object detection with only concept names. In this paper, we address the challenging problem of zero-shot object detection with natural language description, which aims to simultaneously detect and recognize novel concept instances with textual descriptions. We propose a novel deep learning framework to jointly learn visual units, visual-unit attention and word-level attention, which are combined to achieve word-proposal affinity by an element-wise multiplication. To the best of our knowledge, this is the first work on zero-shot object detection with textual descriptions. Since there is no directly related work in the literature, we investigate plausible solutions based on existing zero-shot object detection for a fair comparison. We conduct extensive experiments on three challenging benchmark datasets. The extensive experimental results confirm the superiority of the proposed model.

PDF Details

AAAI Conference 2018 Conference Paper

Balanced Clustering via Exclusive Lasso: A Pragmatic Approach

Zhihui Li
Feiping Nie
Xiaojun Chang
Zhigang Ma
Yi Yang

Clustering is an effective technique in data mining to generate groups that are the matter of interest. Among various clustering approaches, the family of k-means algorithms and min-cut algorithms gain most popularity due to their simplicity and efﬁcacy. The classical k-means algorithm partitions a number of data points into several subsets by iteratively updating the clustering centers and the associated data points. By contrast, a weighted undirected graph is constructed in min-cut algorithms which partition the vertices of the graph into two sets. However, existing clustering algorithms tend to cluster minority of data points into a subset, which shall be avoided when the target dataset is balanced. To achieve more accurate clustering for balanced dataset, we propose to leverage exclusive lasso on k-means and min-cut to regulate the balance degree of the clustering results. By optimizing our objective functions that build atop the exclusive lasso, we can make the clustering result as much balanced as possible. Extensive experiments on several large-scale datasets validate the advantage of the proposed algorithms compared to the state-of-the-art clustering algorithms.

PDF Details

AAAI Conference 2018 Conference Paper

Multi-Rate Gated Recurrent Convolutional Networks for Video-Based Pedestrian Re-Identification

Zhihui Li
Lina Yao
Feiping Nie
Dingwen Zhang
Min Xu

Matching pedestrians across multiple camera views has attracted lots of recent research attention due to its apparent importance in surveillance and security applications. While most existing works address this problem in a still-image setting, we consider the more informative and challenging video-based person re-identiﬁcation problem, where a video of a pedestrian as seen in one camera needs to be matched to a gallery of videos captured by other non-overlapping cameras. We employ a convolutional network to extract the appearance and motion features from raw video sequences, and then feed them into a multi-rate recurrent network to exploit the temporal correlations, and more importantly, to take into account the fact that pedestrians, sometimes even the same pedestrian, move in different speeds across different camera views. The combined network is trained in an end-to-end fashion, and we further propose an initialization strategy via context reconstruction to largely improve the performance. We conduct extensive experiments on the iLIDS-VID and PRID-2011 datasets, and our experimental results conﬁrm the effectiveness and the generalization ability of our model.

PDF Details

AAAI Conference 2018 Conference Paper

Trace Ratio Optimization With Feature Correlation Mining for Multiclass Discriminant Analysis

Forough Rezaei Boroujeni
Sen Wang
Zhihui Li
Nicholas West
Bela Stantic
Lina Yao
Guodong Long

Fisher’s linear discriminant analysis is a widely accepted dimensionality reduction method, which aims to ﬁnd a transformation matrix to convert feature space to a smaller space by maximising the between-class scatter matrix while minimising the within-class scatter matrix. Although the fast and easy process of ﬁnding the transformation matrix has made this method attractive, overemphasizing the large class distances makes the criterion of this method suboptimal. In this case, the close class pairs tend to overlap in the subspace. Despite different weighting methods having been developed to overcome this problem, there is still a room to improve this issue. In this work, we study a weighted trace ratio by maximising the harmonic mean of the multiple objective reciprocals. To further improve the performance, we enforce the 2, 1-norm to the developed objective function. Additionally, we propose an iterative algorithm to optimise this objective function. The proposed method avoids the domination problem of the largest objective, and guarantees that no objectives will be too small. This method can be more beneﬁcial if the number of classes is large. The extensive experiments on different datasets show the effectiveness of our proposed method when compared with four state-of-the-art methods.

PDF Details