Search Results for author:
Found 3 papers, 3 papers with code
Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning
This paper further investigates the necessity of disentangled representation in downstream applications.
An Empirical Study on Disentanglement of Negative-free Contrastive Learning
In this paper, we examine negative-free contrastive learning methods to study the disentanglement property empirically.
Real Additive Margin Softmax for Speaker Verification
The additive margin softmax (AM-Softmax) loss has delivered remarkable performance in speaker verification.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
