Meta-learning methods typically follow a two-loop framework, where each ...
Existing multi-view representation learning methods typically follow a
s...
Learning with noisy labels (LNL) aims to ensure model generalization giv...
Sample selection is an effective strategy to mitigate the effect of labe...
Label noise significantly degrades the generalization ability of deep mo...
Unsupervised domain adaptation (UDA) enables a learning machine to adapt...
This paper aims to address few-shot semantic segmentation. While existin...
Few-shot learning deals with the fundamental and challenging problem of
...
The Cobb angle that quantitatively evaluates the spinal curvature plays ...
In this work, we introduce kernels with random Fourier features in the
m...
Positron emission tomography (PET) imaging is an imaging modality for
di...