Search Results for author:
Found 3 papers, 0 papers with code
Aggregative Self-Supervised Feature Learning from a Limited Sample
Then, in self-aggregative SSL, we propose to self-complement an existing proxy task with an auxiliary loss function based on a linear centered kernel alignment metric, which explicitly promotes the exploring of where are uncovered by the features learned from a proxy task at hand to further boost the modeling capability.
Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
To this end, self-supervised learning (SSL), as a potential solution for deficient annotated data, attracts increasing attentions from the community.
Human Recognition Using Face in Computed Tomography
With the mushrooming use of computed tomography (CT) images in clinical decision making, management of CT data becomes increasingly difficult.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
