Agree to Disagree: Exploring Partial Semantic Consistency against Visual Deviation for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts from known
sub-concepts. However, it is still challenging since the intricate interaction between sub …
sub-concepts. However, it is still challenging since the intricate interaction between sub …
Cross-domain prototype similarity correction for few-shot radar modulation signal recognition
J Gao, S Jiang, X Ji, C Shen - Signal Processing, 2024 - Elsevier
The new classes of radar signals are increasingly difficult to acquire under non-cooperative
environments, which makes it difficult to support convolutional neural network training with …
environments, which makes it difficult to support convolutional neural network training with …
CGProNet: Continual Graph-based Prototypical Networks for Few-Shot Skin Disease Classification
A Noman, Z Beiji, C Zhu, M Alhabib, R Al-Sabri - 2024 - researchsquare.com
The prototypical network effectively classifies skin diseases in few-shot learning but faces
challenges with prototype accuracy due to limited data and insufficient long-term knowledge …
challenges with prototype accuracy due to limited data and insufficient long-term knowledge …