Results 271 to 280 of about 2,239,555 (323)

Prototype Augmentation and Self-Supervision for Incremental Learning

Computer Vision and Pattern Recognition, 2021
Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally.
Fei Zhu, Xu-Yao Zhang, Chuan Wang, Fei Yin, Cheng-Lin Liu   +4 more
semanticscholar   +1 more source

Rethinking Federated Learning with Domain Shift: A Prototype View

Computer Vision and Pattern Recognition, 2023
Federated learning shows a bright promise as a privacy-preserving collaborative learning technique. However, prevalent solutions mainly focus on all private data sampled from the same domain.
Wenke Huang, Mang Ye, Zekun Shi, He Li, Bo Du   +4 more
semanticscholar   +1 more source

Holistic Prototype Activation for Few-Shot Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
Conventional deep CNN-based segmentation approaches have achieved satisfactory performance in recent years, however, they are essentially Big Data-driven technologies and are difficult to generalize to unseen categories.
Gong Cheng, Chunbo Lang, Junwei Han
semanticscholar   +1 more source

Prototype Mixture Models for Few-shot Semantic Segmentation

European Conference on Computer Vision, 2020
Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ...
Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye   +4 more
semanticscholar   +1 more source

Part-aware Prototype Network for Few-shot Semantic Segmentation

European Conference on Computer Vision, 2020
Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications.
Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He   +3 more
semanticscholar   +1 more source

SPNet: Siamese-Prototype Network for Few-Shot Remote Sensing Image Scene Classification

IEEE Transactions on Geoscience and Remote Sensing, 2021
Few-shot image classification has attracted extensive attention, which aims to recognize unseen classes given only a few labeled samples. Due to the large intraclass variances and interclass similarity of remote sensing scenes, the task under such ...
Gong Cheng, Liming Cai, Chunbo Lang, Xiwen Yao, Jinyong Chen, Lei Guo, Junwei Han   +6 more
semanticscholar   +1 more source

Virtual Video Prototyping

Human-Computer Interaction, 2006
Computing power is an integrated part of our physical environment, and since our physical environment is three-dimensional, the virtual studio technology, with its unique potential for visualizing digital 3D objects and environments along with physical objects, offers an obvious path to pursue in order to envision future usage scenarios in the domain ...
Halskov, Kim, Nielsen, Rune
openaire   +2 more sources

Variational Prototype Learning for Deep Face Recognition

Computer Vision and Pattern Recognition, 2021
Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.
Jiankang Deng, J. Guo, Jing Yang, Alexandros Lattas, S. Zafeiriou   +4 more
semanticscholar   +1 more source