Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
AdaDFKD: Exploring adaptive inter-sample relationship in data-free knowledge distillation
AbstractIn scenarios like privacy protection or large-scale data transmission, data-free knowledge distillation (DFKD) methods are proposed to learn Knowledge Distillation (KD) when data is not accessible. They generate pseudo samples by extracting the ...
- research-articleJuly 2024
BiU-net: A dual-branch structure based on two-stage fusion strategy for biomedical image segmentation
Computer Methods and Programs in Biomedicine (CBIO), Volume 252, Issue CJul 2024https://doi.org/10.1016/j.cmpb.2024.108235Highlights- The proposed novel network for medical image segmentation outperforms some SOTA models on four datasets.
- Dual-branch encoder effectively captures the local features and models long-distance dependencies.
- Two-stage fusion strategy ...
Computer-based biomedical image segmentation plays a crucial role in planning of assisted diagnostics and therapy. However, due to the variable size and irregular shape of the segmentation target, it is still a challenge ...
- research-articleApril 2024
A method based on VMD improved by SSA for leak location of water distribution
Digital Signal Processing (DISP), Volume 145, Issue CFeb 2024https://doi.org/10.1016/j.dsp.2023.104334ABSTRACTLeak location using cross-correlation of acoustic signals collected by acceleration sensors is easily disturbed by the environmental noises resulting in inaccurate identification of its location, especially at low SNR. Aiming at this problem, an ...
- research-articleOctober 2023
Hierarchical Knowledge Propagation and Distillation for Few-Shot Learning
Neural Networks (NENE), Volume 167, Issue COct 2023, Pages 615–625https://doi.org/10.1016/j.neunet.2023.08.040AbstractRecent research efforts on Few-Shot Learning (FSL) have achieved extensive progress. However, the existing efforts primarily focus on the transductive setting of FSL, which is heavily challenged by the limited quantity of the unlabeled query set. ...
Highlights- We highlight the significance of the inductive Few-Shot Learning in the real-world settings.
- The existing inductive FSL methods usually ignore the relations between sample-level and class-level representations.
- The proposed HKPD ...
- research-articleSeptember 2023
Dynamic data-free knowledge distillation by easy-to-hard learning strategy
Information Sciences: an International Journal (ISCI), Volume 642, Issue CSep 2023https://doi.org/10.1016/j.ins.2023.119202AbstractData-free knowledge distillation (DFKD) is a widely-used strategy for Knowledge Distillation (KD) whose training data is not available. It trains a lightweight student model with the aid of a large pretrained teacher model without any ...
-
- research-articleSeptember 2023
Transformer-based feature interactor for person re-identification with margin self-punishment loss
Image and Vision Computing (IAVC), Volume 137, Issue CSep 2023https://doi.org/10.1016/j.imavis.2023.104752AbstractPerson re-identification aims to retrieve specific pedestrians from different cameras and scenes, in which extracting robust and discriminative features is crucial for this task. To explore the potential interactions among images and learn more ...
Highlights- A Transformer-based network for multi-scale information interaction.
- Constructing context-aware features containing global information and detailed features with pyramidal attention.
- Adaptive penalty margin for tighter custom ...
- research-articleAugust 2023
FedME<sup>2</sup>: Memory Evaluation & Erase Promoting Federated Unlearning in DTMN
IEEE Journal on Selected Areas in Communications (JSAC), Volume 41, Issue 11Nov. 2023, Pages 3573–3588https://doi.org/10.1109/JSAC.2023.3310049Digital Twins (DTs) can generate digital replicas for mobile networks (MNs) that accurately reflect the state of MN. Machine learning (ML) models trained in DT for MN (DTMN) virtual environments can be more robustly implemented in MN. This can avoid the ...
- research-articleJune 2023
FedCrack: Federated Transfer Learning With Unsupervised Representation for Crack Detection
IEEE Transactions on Intelligent Transportation Systems (ITS-TRANSACTIONS), Volume 24, Issue 10Oct. 2023, Pages 11171–11184https://doi.org/10.1109/TITS.2023.3286439Empowered by labeled datasets, supervised pre-training based transfer learning (SPTL) has made significant advances for image classification applications. However, due to privacy-preserving protocol and unaccessible annotation, it emerges as a novel ...
- research-articleMay 2023
Scene Graph Semantic Inference for Image and Text Matching
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Volume 22, Issue 5Article No.: 144, Pages 1–23https://doi.org/10.1145/3563390With the rapid development of information technology, image and text data have increased dramatically. Image and text matching techniques enable computers to understand information from both visual and text modalities and match them based on semantic ...
- research-articleMarch 2023
Semantic-Oriented Feature Coupling Transformer for Vehicle Re-Identification in Intelligent Transportation System
IEEE Transactions on Intelligent Transportation Systems (ITS-TRANSACTIONS), Volume 25, Issue 3March 2024, Pages 2803–2813https://doi.org/10.1109/TITS.2023.3257873More robust intelligent transportation systems including autonomous driving systems are in full flourish with the revolution of deep learning and the 6G wireless communication network. Vehicle Re-Identification, an indispensable branch of the intelligent ...
- research-articleMarch 2023
Improving topic disentanglement via contrastive learning
Information Processing and Management: an International Journal (IPRM), Volume 60, Issue 2Mar 2023https://doi.org/10.1016/j.ipm.2022.103164AbstractWith the emergence and development of deep generative models, such as the variational auto-encoders (VAEs), the research on topic modeling successfully extends to a new area: neural topic modeling, which aims to learn disentangled ...
Highlights- We propose the contrastive disentangled neural topic model based on topic embedding.
- research-articleFebruary 2023
LORE: logical location regression network for table structure recognition
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceFebruary 2023, Article No.: 333, Pages 2992–3000https://doi.org/10.1609/aaai.v37i3.25402Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes, or learning to generate the corresponding markup ...
- research-articleDecember 2022
Gaussian-based probability fusion for person re-identification with Taylor angular margin loss
Neural Computing and Applications (NCAA), Volume 34, Issue 23Dec 2022, Pages 20639–20653https://doi.org/10.1007/s00521-022-07496-8AbstractPerson re-identification (ReID) aims to match the specific pedestrians in the public environment with cross-domain cameras. Posture change, occlusion, and viewpoint change complicate ReID. Representation learning and metric learning have been ...
- research-articleOctober 2022
Clustered federated learning multi-classifier for non-IID scenario in drone devices
DroneCom '22: Proceedings of the 5th International ACM Mobicom Workshop on Drone Assisted Wireless Communications for 5G and BeyondOctober 2022, Pages 79–84https://doi.org/10.1145/3555661.3560868Existing machine learning technology lacks effective support for practical drone devices in target recognition. The Clustered Federated Learning Algorithm (C-FLA) was proposed to enhance the joint training in drone groups. The algorithm considered the ...
- research-articleAugust 2022
Efficient but lightweight network for vehicle re-identification with center-constraint loss
Neural Computing and Applications (NCAA), Volume 34, Issue 15Aug 2022, Pages 12373–12384https://doi.org/10.1007/s00521-021-06658-4AbstractVehicle re-identification aims to retrieve the target vehicle from the image gallery quickly and accurately. Vehicle re-identification with deep learning has achieved considerable performance. However, most popular methods need construct complex ...
- research-articleJuly 2022
Cross-modal image retrieval with deep mutual information maximization
Neurocomputing (NEUROC), Volume 496, Issue CJul 2022, Pages 166–177https://doi.org/10.1016/j.neucom.2022.01.078AbstractIn this paper, we study the cross-modal image retrieval, where the inputs contain a source image plus some text that describes certain modifications to this image and the desired image. Prior work usually uses a three-stage strategy to ...
- research-articleJune 2022
TriEP: Expansion-Pool TriHard Loss for Person Re-Identification
Neural Processing Letters (NPLE), Volume 54, Issue 3Jun 2022, Pages 2413–2432https://doi.org/10.1007/s11063-021-10736-yAbstractPerson re-identification aims to identify the same person across different cameras, which is widely applied in the intelligent monitoring field. The research of TriHard loss has been verified to improve performance efficiently in the person re-...
- research-articleJune 2022
Joining features by global guidance with bi-relevance trihard loss for person re-identification
Neural Computing and Applications (NCAA), Volume 34, Issue 11Jun 2022, Pages 8697–8712https://doi.org/10.1007/s00521-021-06852-4AbstractPerson re-identification (ReID) aims to associate the person with the given identity across different cameras, which has wide application in the field of intelligent video. In this work, an efficient method is proposed to improve ReID performance. ...
- research-articleApril 2022
A new multikernel relevance vector machine based on the HPSOGWO algorithm for predicting and controlling blast-induced ground vibration
Engineering with Computers (ENGC), Volume 38, Issue 2Apr 2022, Pages 1905–1920https://doi.org/10.1007/s00366-020-01136-2AbstractThe relevance vector machine (RVM) is considered a robust machine learning method and its superior performance has been confirmed through many successful engineering applications. To improve the performance of the RVM model, three single kernel ...
- research-articleMarch 2022
Multi-attribute adaptive aggregation transformer for vehicle re-identification
Information Processing and Management: an International Journal (IPRM), Volume 59, Issue 2Mar 2022https://doi.org/10.1016/j.ipm.2022.102868Highlights- A vehicle attribute transformer for vehicle re-identification is proposed, which can aggregate the attributes of vehicle model, color and viewpoint ...
With the continuous development of intelligent transportation systems, vehicle-related fields have emerged a research boom in detection, tracking, and retrieval. Vehicle re-identification aims to judge whether a specific vehicle ...