Search Results for author:
Found 3 papers, 1 papers with code
From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers
We introduce multi-phase training of audio spectrogram transformers by connecting the seminal idea of coarse-to-fine with transformer models.
FlexiAST: Flexibility is What AST Needs
To overcome this limitation, this paper proposes a training procedure to provide flexibility to standard AST models without architectural changes, allowing them to work with various patch sizes at the inference stage - FlexiAST.
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
