Learning background prompts to discover implicit knowledge for open vocabulary object detection

J Li, J Zhang, J Li, G Li, S Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable
of recognizing objects from both base and novel categories. Recent advances leverage …

Alignsam: Aligning segment anything model to open context via reinforcement learning

D Huang, X Xiong, J Ma, J Li, Z Jie… - Proceedings of the …, 2024 - openaccess.thecvf.com
Powered by massive curated training data Segment Anything Model (SAM) has
demonstrated its impressive generalization capabilities in open-world scenarios with the …

SCFormer: Spectral coordinate transformer for cross-domain few-shot hyperspectral image classification

J Li, Z Zhang, R Song, Y Li, Q Du - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
Cross-domain (CD) hyperspectral image classification (HSIC) has been significantly
boosted by methods employing Few-Shot Learning (FSL) based on CNNs or GCNs …

Inter-domain mixup for semi-supervised domain adaptation

J Li, G Li, Y Yu - Pattern Recognition, 2024 - Elsevier
Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain
distributions, with a small number of target labels available, achieving better classification …

Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation

BH Ngo, NT Do-Tran, TN Nguyen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Most domain adaptation (DA) methods are based on either a convolutional neural networks
(CNNs) or a vision transformers (ViTs). They align the distribution differences between …

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

J Li, G Li, H Cheng, Z Liao, Y Yu - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Federated learning with noisy labels (F-LNL) aims at seeking an optimal server model via
collaborative distributed learning by aggregating multiple client models trained with local …

Adaptive Graph Learning with Semantic Promotability for Domain Adaptation

Z Zheng, S Teng, L Teng, W Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Domain Adaptation (DA) is used to reduce cross-domain differences between the labeled
source and unlabeled target domains. As the existing semantic-based DA approaches …

Partial label learning with heterogeneous domain adaptation

L Zhao, Y Xiao, B Liu - Neurocomputing, 2024 - Elsevier
Partial label learning (PLL) seeks a classification model with partially labeled (PL) instances.
Each PL instance is attached with a candidate label set, with only one being ground-truth. A …

Semi-Supervised Detection of Detailed Ground Feature Changes and Its Impact on Land Surface Temperature

P Wu, J Liang, J Xu, K Zhong, H Hu, J Zuo - Atmosphere, 2023 - mdpi.com
This paper presents a semi-supervised change detection optimization strategy as a means
to mitigate the reliance of unsupervised/semi-supervised algorithms on pseudo-labels. The …

HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation

BH Ngo, DC Bui, NT Do-Tran, TJ Choi - arXiv preprint arXiv:2412.11819, 2024 - arxiv.org
The enhanced representational power and broad applicability of deep learning models have
attracted significant interest from the research community in recent years. However, these …