Results 11 to 20 of about 2,239,555 (323)
FedProto: Federated Prototype Learning across Heterogeneous Clients [PDF]
AAAI Conference on Artificial Intelligence, 2021 Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space.
Yue Tan +6 more
semanticscholar +1 more source
Adaptive Prototype Learning and Allocation for Few-Shot Segmentation [PDF]
Computer Vision and Pattern Recognition, 2021 Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information.
Gen Li +5 more
semanticscholar +1 more source
Rethinking Semantic Segmentation: A Prototype View [PDF]
Computer Vision and Pattern Recognition, 2022 Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax ...
Tianfei Zhou +3 more
semanticscholar +1 more source
Metaverse for Social Good: A University Campus Prototype [PDF]
ACM Multimedia, 2021 In recent years, the metaverse has attracted enormous attention from around the world with the development of related technologies. The expected metaverse should be a realistic society with more direct and physical interactions, while the concepts of ...
Haihan Duan +5 more
semanticscholar +1 more source
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation [PDF]
Computer Vision and Pattern Recognition, 2022 Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs. Existing methods often rely on Class Activation Mapping (CAM) that measures the correlation between image pixels and ...
Qi Chen +3 more
semanticscholar +1 more source
Learning Normal Dynamics in Videos with Meta Prototype Network [PDF]
Computer Vision and Pattern Recognition, 2021 Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than those of normal ...
Hui Lv +5 more
semanticscholar +1 more source
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation [PDF]
International Joint Conference on Artificial Intelligence, 2021 We study a practical domain adaptation task, called source-free unsupervised domain adaptation (UDA) problem, in which we cannot access source domain data due to data privacy issues but only a pre-trained source model and unlabeled target data are ...
Zhen Qiu +6 more
semanticscholar +1 more source
Cross-modal Prototype Driven Network for Radiology Report Generation [PDF]
European Conference on Computer Vision, 2022 Radiology report generation (RRG) aims to describe automatically a radiology image with human-like language and could potentially support the work of radiologists, reducing the burden of manual reporting.
Jun Wang, A. Bhalerao, Yulan He
semanticscholar +1 more source
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment [PDF]
IEEE International Conference on Computer Vision, 2019 Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories.
Kaixin Wang +4 more
semanticscholar +1 more source
Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning [PDF]
Computer Vision and Pattern Recognition, 2021 Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and prototype reorganization can only be achieved under little supervision ...
Kai Zhu +4 more
semanticscholar +1 more source