Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks183 from public data
- MambaHSI: Spatial–Spectral Mamba for Hyperspectral Image Classification363
This work proposes a novel HSI classification model based on a Mamba model, named MambaHSI, which can simultaneously model long-range interaction of the whole image and integrate spatial and spectral information in an adaptive manner, and is the first image-level HSI classification model based on the Mamba.
- Tensor Canonical Correlation Analysis for Multi-View Dimension Reduction250
TCCA is developed, which straightforwardly yet naturally generalizes CCA to handle the data of an arbitrary number of views by analyzing the covariance tensor of the different views, and proves that the main problem of multi-view canonical correlation maximization is equivalent to finding the best rank-1 approximation of the data covariance Tensor.
- 185
- Multiview Matrix Completion for Multilabel Image Classification160
Experimental evaluation on two real-world data sets demonstrate the effectiveness of MVMC for transductive (semisupervised) multilabel image classification, and show that MVMC can exploit complementary properties of different features and output-consistent labels for improved multilabe image classification.
- Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification154
This work introduces multiview vector-valued manifold regularization (MV3MR), which exploits the complementary property of different features and discovers the intrinsic local geometry of the compact support shared by different features under the theme of manifoldRegularization.
- Low-Rank Multi-View Learning in Matrix Completion for Multi-Label Image Classification139
This work presents a novel multi-view learning model for MC-based image classification, called low-rank multi- view matrix completion (lrMMC), which first seeks a low-dimensional common representation of all views by utilizing the proposed low- rank multi-View learning (lrVVL) algorithm.
- Decomposition-Based Transfer Distance Metric Learning for Image Classification118
This paper considers the transfer learning setting by exploiting the large quantity of side information from certain related, but different source tasks to help with target metric learning (with only a little side information), and proposes a decomposition-based transfer DML (DTDML).
- Learning from models beyond fine-tuning114
This Review provides a comprehensive overview of current methods based on foundation models from the perspective of LFM, and emphasizes that maximizing the use of parametric knowledge in data-scarce scenarios is critical to LFM.
- Towards understanding the power of quantum kernels in the NISQ era106
This work proves that the advantage of quantum kernels is vanished for large size of datasets, few number of measurements, and large system noise and provides theoretical guidance of exploring advanced quantum kernels to attain quantum advantages on NISQ devices.
- 106
- Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification106
A novel large margin multi- modal multi-task feature extraction (LM3FE) framework for handling multi-modal features for image classification that utilizes the complementarity of different modalities to further help reduce feature redundancy in each modality.
- Cost-Sensitive Feature Selection by Optimizing F-Measures105
An effective feature selection algorithm that explores the class imbalance issue by optimizing F-measures and selects features corresponding to the best F-measure, which will fully represent the properties of all classes.
- Transferring Knowledge Fragments for Learning Distance Metric from a Heterogeneous Domain94
This paper examines the problem of transfer distance metric learning (DML), which usually aims to mitigate the label information deficiency issue in the target DML, and develops novel algorithm to learn either linear or nonlinear target metric.
- 91
- Parameter Efficient Multi-task Model Fusion with Partial Linearization79
This work proposes a novel method to improve multi-task fusion for parameter-efficient fine-tuning techniques like LoRA fine-tuning, which partially linearizes only the adapter modules and applies task arithmetic over the linearized adapters.
- A fault diagnosis method based on one-dimensional data enhancement and convolutional neural network72
A fault diagnosis method based on one-dimensional data enhancement and convolutional neural network (CNN) is proposed that can improve the training accuracy and the test accuracy under the premise of ensuring the diagnosis efficiency when there are many fault types and few training data in the experimental data set.
- DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices67
This work proposes a collaborative inference framework termed DeViT to facilitate edge deployment by decomposing large ViTs, and designs a decomposition-and-ensemble algorithm based on knowledge distillation, termed DEKD, to fuse multiple small decomposed models while dramatically reducing communication overheads.
- Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning65
A lightweight autoencoder-based method to compress the large intermediate feature of DNN, then a multi-agent hybrid proximal policy optimization (MAHPPO) algorithm to solve the optimization problem with a hybrid action space is proposed.
- WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge58
A plug-in framework named WisdoM, to leverage the contextual world knowledge induced from the large vision-language models (LVLMs) for enhanced MSA, and to reduce the noise in the context, a training-free contextual fusion mechanism is designed.
- CLNode: Curriculum Learning for Node Classification55
Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.
- LGViT: Dynamic Early Exiting for Accelerating Vision Transformer53
A novel two-stage training scheme is developed, including end-to-end training and self-distillation with the backbone frozen to generate early exiting ViTs, which facilitates the fusion of global and local information extracted by the two types of heads.
- Vector-Valued Multi-View Semi-Supervsed Learning for Multi-Label Image Classification51
The proposed multi-view vector-valued manifold regularization (MV$^3$MR) methodology for image classification exploits the complementary properties of different features, and discovers the intrinsic local geometry of the compact support shared by different features under the theme of manifoldRegularization.
- CDFKD-MFS: Collaborative Data-Free Knowledge Distillation via Multi-Level Feature Sharing45
This work proposes a framework termed collaborative data-free knowledge distillation via multi-level feature sharing (CDFKD-MFS), which consists of a multi-header student module, an asymmetric adversarial data- free KD module, and an attention-based aggregation module.
- Pitch-density-based features and an SVM binary tree approach for multi-class audio classification in broadcast news45
Experiments show that the proposed one-dimensional APD and RTPD features are able to achieve comparable accuracy with popular high-dimensional features in speech/music discrimination, and the SVM-BT approach demonstrates superior performance in multi-class audio classification.
- ResumeGAN42
A novel framework is proposed that targets the same task, but integrate different types of information in a more sophisticated way and introduce adversarial learning to learn more expressive representation and the effectiveness of the framework is demonstrated by extensive experiments.
- Heterogeneous Multitask Metric Learning Across Multiple Domains42
To appropriately handle multiple domains, a novel heterogeneous MTML (HMTML) framework is developed, which can effectively explore high-order statistics, thus obtaining more reliable feature transformations and metrics.
- Pre-Trained Multi-View Word Embedding Using Two-Side Neural Network39
A two-side multimodal neural network is proposed to learn a robust word embedding from multiple data sources including free text, user search queries and search click-through data and outperforms state-of-the-art word embeddedding algorithm with each individual source.
- 37
- 37
- 36
- A characteristic set method for ordinary difference polynomial systems31
An algorithm to decompose the zero set of a finite set of difference polynomials into the union of zero sets of certain ascending chains is proposed and used to solve the perfect ideal membership problem, and to prove certain difference identities automatically.
- Transition role of entangled data in quantum machine learning30
The authors prove that the impact of entangled data on prediction error exhibits a dual effect, depending on the number of permitted measurements, and show that this is not the case when the allowed number of measurements to incoherently learn quantum dynamics is low.
- Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging29
An efficient-and-effective WEMoE (E-WEMoE) method, whose core mechanism involves eliminating non-essential elements in the critical modules of WEMoE and implementing shared routing across multiple MoE modules, thereby significantly reducing both the trainable parameters, the overall parameter count, and computational overhead of the merged model by WEMoE.
- ResumeNet: A Learning-Based Framework for Automatic Resume Quality Assessment27
A neural-network model is designed to predict the quality of each resume, where some text processing techniques are incorporated and several variants of the model are proposed by utilizing the pair/triplet-based loss, or introducing some semi-supervised learning technique to make use of the abundant unlabeled data.
- SGDA: Towards 3-D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention26
A slice grouped domain attention (SGDA) module is proposed to enhance the generalization capability of the pulmonary nodule detection networks and enables substantially better multi- domain pulmonary nodules detection performance compared with the state-of-the-art multi-domain learning methods.
- 26
- 26
- PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation23
This work proposes PrimKD, a knowledge distillation based approach that focuses on guided multimodal fusion, with an emphasis on leveraging the primary RGB modality, and utilizes a model trained exclusively on the RGB modality as the teacher, guiding the learning process of a student model that fuses both RGB and depth modalities.
- 23
- 22
- 22
- 20
- Transfer metric learning: algorithms, applications and outlooks20
A systematic review of the TML literature is presented, group TML into different categories according to different settings and metric transfer strategies, such as direct metric approximation, subspace approximation, distance approximation, and distribution approximation.
- 20
- 18
- 18
- 17
- 16
- 15
- Online Heterogeneous Transfer Metric Learning15
The proposed online HTML (OHTML) method formulate the problem in the online setting so that the optimization is efficient and the model can be adapted to new coming data and demonstrates both effectiveness and efficiency of the proposed method.
- 14
- 14
- 14
- 12
- 12
- 12
- Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm12
This work presents an integrated multiple deep learning models reuse and prediction strategy, which greatly increases the feasibility of the digital retina in processing and analyzing the large-scale visual data in smart cities.
- General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer12
This work develops a general and flexible heterogeneous TDML (HTDML) framework based on the knowledge fragment transfer strategy, which demonstrates superiority of the proposed method on both scene classification and object recognition.
- Region-adaptive Concept Aggregation for Few-shot Visual Recognition11
A novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net is proposed, which devise a region- Adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation.
- Intrinsic Performance Influence-based Participant Contribution Estimation for Horizontal Federated Learning11
A novel contribution estimation method is proposed: Intrinsic Performance Influence-based Contribution Estimation (IPICE), which assigns small contributions to bad/garbage data and thus prevent them from participating and deteriorating the learning ecosystem.
- Not All Instances Contribute Equally: Instance-Adaptive Class Representation Learning for Few-Shot Visual Recognition11
This work develops an adaptive instance revaluing network (AIRN) with the capability to address the biased representation issue when generating the class representation, by learning and assigning adaptive weights for different instances according to their relative significance in the support set of corresponding class.
- 11
- 10
- 10
- 9
- 9
- 8
- 8
- 8
- 8
- CoFormer: Collaborating With Heterogeneous Edge Devices for Scalable Transformer Inference7
CoFormer enables the efficient inference of GPT2-XL with 1.6 billion parameters on edge devices, reducing memory requirements by 76.3%.
- Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets7
For the first time, SFL is introduced into HFL and a novel algorithm adapted to this combined framework, called Fed-CHS is proposed, which provides evidence of the superiority of the superiority of the proposed Fed-CHS on both communication overhead saving and test accuracy over baseline methods.
- Federated Learning With Only Positive Labels by Exploring Label Correlations7
This article proposes a novel and generic method termed federated averaging (FedAvg) by exploring label correlations (FedALCs), which estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- Data-Adaptive Weight-Ensembling for Multi-task Model Fusion3
This work proposes a data-adaptive weight-ensembling approach that generates model weights in time for unified model fusion, demonstrating superior performance and satisfactory zero-shot transferability on vision Transformers and Flan-T5 models.
- 3
- 3
- 3
- 3
- 3
- Deep Heterogeneous Multi-Task Metric Learning for Visual Recognition and Retrieval3
A deep heterogeneous MTML (DHMTML) method, in which a nonlinear mapping is learned for each task by using a deep neural network, which outperforms single-task deep metric learning algorithms and other HMTML approaches consistently on several benchmark datasets.
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- DM-PCL: Text-Driven Dual-Modal Prototype Consistency Learning for Weakly-Supervised Few-Shot Part Segmentation2
Text-driven dual-modal prototype consistency learning (DM-PCL) is proposed, which predicts pseudo masks for both support and query images using part-level textual labels and learns consistent part prototypes across diverse images and modalities to facilitate accurate part segmentation.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation1
AiDE-Q is proposed, an effective framework that addresses the challenge of quantum many-body problems by iteratively generating high-quality synthetic labeled datasets and paves the way for more efficient and practical applications of DL for quantum property estimation.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Patch Alignment for Graph Embedding–
This paper presents locally linear embedding (LLE), which uses linear coefficients, which reconstruct a given example by its neighbors, to represent the local geometry, and then seeks a low-dimensional embedding, in which these coefficients are still suitable for reconstruction.
- –
- –
- –
- Optimality Conditions for Nonsmooth Multiobjective Fractional Programming with (F,α,ρ,d)-V-Convexity–
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.