Yaojin Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yaojin Lin has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
Chenxi Wang
5 shared publicationsJinkun Chen
School of Mathematics and Statistics, Minnan Normal University, Zhangzhou, China
4 shared publications- Xuegang Hu
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China
4 shared publications - Haoyang Liu
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
3 shared publications - Jinghua Liu
Xiamen Key Laboratory of Computer Vision and Pattern Recognition, Huaqiao University, Xiamen, China
3 shared publications - Peipei Li
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
3 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 34 (10) , 3251-3263
A Fuzzy Rough Set Framework for Interval-Valued Multilabel Feature Selection With Label Enhancement
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 34 (10) , 3251-3263
A Fuzzy Rough Set Framework for Interval-Valued Multilabel Feature Selection With Label Enhancement
- 22 July 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (8) , 393
Feature selection for label distribution learning based on embedding mutual information optimization
- 22 July 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (8) , 393
Feature selection for label distribution learning based on embedding mutual information optimization
- Open Access
- 19 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (4) , 1-24
LSPEL: Label-Specific Feature-Based Partial Label Learning for Emerging New Labels
In partial label learning (PLL) tasks, each training instance is assigned a candidate label set, with only one label being correct. Previous studies on PLL have focused on scenarios where the class label set remains fixed, i.e., the label set for test data is the same as that used during training. However, in many real-world applications, the environment is dynamic, and new labels may emerge, requiring methods that can detect and classify these new labels. Moreover, previous methods typically learn from partial label data by manipulating the same feature set, which may be suboptimal as it overlooks the semantic relationships between instances and labels. To this end, we develop a novel PLL approach called Label-Specific feature-based Partial label learning with Emerging new Labels (LSPEL), which works by iteratively learning label-specific features during the label disambiguation process to support new label detection and model update. It consists of three key components: (1) model training based on label-specific feature learning, (2) construction of a new label detector that works in conjunction with the classifier to predict known labels, and (3) model updating and induction to further enhance the prediction results for known labels. Extensive experiments on synthetic and real-world PL datasets demonstrate that LSPEL is effective in handling emerging new labels.
- 19 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (4) , 1-24
Open AccessLSPEL: Label-Specific Feature-Based Partial Label Learning for Emerging New Labels
In partial label learning (PLL) tasks, each training instance is assigned a candidate label set, with only one label being correct. Previous studies on PLL have focused on scenarios where the class label set remains fixed, i.e., the label set for test data is the same as that used during training. However, in many real-world applications, the environment is dynamic, and new labels may emerge, requiring methods that can detect and classify these new labels. Moreover, previous methods typically learn from partial label data by manipulating the same feature set, which may be suboptimal as it overlooks the semantic relationships between instances and labels. To this end, we develop a novel PLL approach called Label-Specific feature-based Partial label learning with Emerging new Labels (LSPEL), which works by iteratively learning label-specific features during the label disambiguation process to support new label detection and model update. It consists of three key components: (1) model training based on label-specific feature learning, (2) construction of a new label detector that works in conjunction with the classifier to predict known labels, and (3) model updating and induction to further enhance the prediction results for known labels. Extensive experiments on synthetic and real-world PL datasets demonstrate that LSPEL is effective in handling emerging new labels.
- 12 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5001-5014
DSPL: Dual-Space Prompt Learning With Context Bias Decoupling for Open Set Recognition
Open Set Recognition (OSR) aims to accurately classify known classes and effectively reject unknown classes in open-world scenarios, which is essential for building safe and reliable intelligent systems. Existing studies have shown that auxiliary data-based methods—utilizing outlier exposure or prompt-based guidance to strengthen OSR models—have achieved significant improvements. However, these methods are highly sensitive to the selection of data. Considering the demand for domain expertise and the cost implications, synthesizing data from known samples becomes a preferable alternative. To achieve performance on par with methods that incorporate auxiliary data, it is essential to address the following key challenges: (1) obtaining meaningful pseudo-unknown samples and prompts without manual intervention, and (2) establishing a reliable recognition mechanism during the inference phase. In this paper, we propose a novel Dual-Space Prompt Learning with Context Bias Decoupling (DSPL) method to address the above issues. Specifically, we symmetrically model the same number of unknown classes as known classes to achieve a balanced class distribution in the embedding space. Learnable textual templates are designed for both types of data. Meanwhile, boundary samples are synthesized and treated as pseudo-unknown samples by decoupling discriminative and co-occurring features. Additionally, unknown sample detection is performed by integrating the maximum posterior over known and unknown classes, thereby extending the advantages of symmetric modeling from the training phase to inference. Extensive experiments demonstrate that the proposed method DSPL achieves state-of-the-art performance compared with the most advanced OSR methods.
- 12 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5001-5014
DSPL: Dual-Space Prompt Learning With Context Bias Decoupling for Open Set Recognition
Open Set Recognition (OSR) aims to accurately classify known classes and effectively reject unknown classes in open-world scenarios, which is essential for building safe and reliable intelligent systems. Existing studies have shown that auxiliary data-based methods—utilizing outlier exposure or prompt-based guidance to strengthen OSR models—have achieved significant improvements. However, these methods are highly sensitive to the selection of data. Considering the demand for domain expertise and the cost implications, synthesizing data from known samples becomes a preferable alternative. To achieve performance on par with methods that incorporate auxiliary data, it is essential to address the following key challenges: (1) obtaining meaningful pseudo-unknown samples and prompts without manual intervention, and (2) establishing a reliable recognition mechanism during the inference phase. In this paper, we propose a novel Dual-Space Prompt Learning with Context Bias Decoupling (DSPL) method to address the above issues. Specifically, we symmetrically model the same number of unknown classes as known classes to achieve a balanced class distribution in the embedding space. Learnable textual templates are designed for both types of data. Meanwhile, boundary samples are synthesized and treated as pseudo-unknown samples by decoupling discriminative and co-occurring features. Additionally, unknown sample detection is performed by integrating the maximum posterior over known and unknown classes, thereby extending the advantages of symmetric modeling from the training phase to inference. Extensive experiments demonstrate that the proposed method DSPL achieves state-of-the-art performance compared with the most advanced OSR methods.
- 2 April 2026
- Published by Elsevier in Neural Networks
- Vol. 201, 108910
Dual CNN and ViT experts fusion for open set recognition
- 2 April 2026
- Published by Elsevier in Neural Networks
- Vol. 201, 108910
Dual CNN and ViT experts fusion for open set recognition
- 18 June 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (10) , 1-14
Multi-granularity decision information integration network for hierarchical classification via local and global constraints
- 18 June 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (10) , 1-14
Multi-granularity decision information integration network for hierarchical classification via local and global constraints
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (5) , 3698-3708
Bidirectional Patch-Aware Attention Network for Few-Shot Learning
Few-shot learning (FSL) aims to train a model using a minimal number of samples and subsequently apply this model to recognize unseen classes. Recently, metric-based methods mainly focus on exploring the relationship between the support set and the query set through attention mechanism in solving FSL problems. However, these methods typically employ unidirectional computation when calculating the attention relationship between support and query. This unidirectional approach not only limits the depth and breadth of knowledge acquisition but may also lead to mismatched patches between support and query, thereby affecting the overall performance of the model. In this article, we propose a bidirectional patch-aware attention network for few-shot learning (BPAN) to address this issue. First, we extract subimages via grid cropping and feed them into the learned feature extractor to obtain patch features. Moreover, self-attention is used to assign different weights to patch features and reconstruct them. Then, PFCAM is proposed to mutually explore the patch feature relationship between the support set and the support set, further reconstruct the patch features, and aggregate multiple patch features of each image into one feature through a learnable parameter matrix for the purpose of prediction. Finally, the template for each class is constructed to extend the results of PFCAM to the few-shot classification scenario. Experiments on three benchmark datasets show that BPAN achieves superior performance.
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (5) , 3698-3708
Bidirectional Patch-Aware Attention Network for Few-Shot Learning
Few-shot learning (FSL) aims to train a model using a minimal number of samples and subsequently apply this model to recognize unseen classes. Recently, metric-based methods mainly focus on exploring the relationship between the support set and the query set through attention mechanism in solving FSL problems. However, these methods typically employ unidirectional computation when calculating the attention relationship between support and query. This unidirectional approach not only limits the depth and breadth of knowledge acquisition but may also lead to mismatched patches between support and query, thereby affecting the overall performance of the model. In this article, we propose a bidirectional patch-aware attention network for few-shot learning (BPAN) to address this issue. First, we extract subimages via grid cropping and feed them into the learned feature extractor to obtain patch features. Moreover, self-attention is used to assign different weights to patch features and reconstruct them. Then, PFCAM is proposed to mutually explore the patch feature relationship between the support set and the support set, further reconstruct the patch features, and aggregate multiple patch features of each image into one feature through a learnable parameter matrix for the purpose of prediction. Finally, the template for each class is constructed to extend the results of PFCAM to the few-shot classification scenario. Experiments on three benchmark datasets show that BPAN achieves superior performance.
- 8 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Hierarchical feature selection via joint local label enhancement and neighborhood label distribution correlation
- 8 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Hierarchical feature selection via joint local label enhancement and neighborhood label distribution correlation
- Open Access
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 740-744
Online multi-label streaming feature selection based on neighborhood rough set with label correlation
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 740-744
Open AccessOnline multi-label streaming feature selection based on neighborhood rough set with label correlation
- Open Access
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 3, 2027-2035
Boosting Zero-shot Stereo Matching Using Large-Scale Mixed Images Sources in the Real World
Stereo matching methods rely on dense pixel-wise ground truth labels, which are laborious to obtain, especially for real-world datasets. The scarcity of labeled data and domain gaps between synthetic and real-world images also pose notable challenges. In this paper, we propose a novel framework, BooSTer, that leverages both vision foundation models and large-scale mixed image sources, including synthetic, real, and single-view images. First, to fully unleash the potential of large-scale single-view images, we design a data generation strategy combining monocular depth estimation and diffusion models to generate dense stereo matching data from single-view images. Second, to tackle sparse labels in real-world datasets, we transfer knowledge from monocular depth estimation models, using pseudo-mono depth labels and a dynamic scale- and shift-invariant loss for additional supervision. Furthermore, we incorporate vision foundation model as an encoder to extract robust and transferable features, boosting accuracy and generalization. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach, achieving significant improvements in accuracy over existing methods, particularly in scenarios with limited labeled data and domain shifts.
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 3, 2027-2035
Open AccessBoosting Zero-shot Stereo Matching Using Large-Scale Mixed Images Sources in the Real World
Stereo matching methods rely on dense pixel-wise ground truth labels, which are laborious to obtain, especially for real-world datasets. The scarcity of labeled data and domain gaps between synthetic and real-world images also pose notable challenges. In this paper, we propose a novel framework, BooSTer, that leverages both vision foundation models and large-scale mixed image sources, including synthetic, real, and single-view images. First, to fully unleash the potential of large-scale single-view images, we design a data generation strategy combining monocular depth estimation and diffusion models to generate dense stereo matching data from single-view images. Second, to tackle sparse labels in real-world datasets, we transfer knowledge from monocular depth estimation models, using pseudo-mono depth labels and a dynamic scale- and shift-invariant loss for additional supervision. Furthermore, we incorporate vision foundation model as an encoder to extract robust and transferable features, boosting accuracy and generalization. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach, achieving significant improvements in accuracy over existing methods, particularly in scenarios with limited labeled data and domain shifts.