1 citations · 1 across the 4 of their papers we have counts for
4 papers
Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition
Qingbo Kang, Jun Gao, Kang Li +1
Masked autoencoder (MAE) has attracted unprecedented attention and achieves remarkable performance in many vision tasks. It reconstructs random masked image patches (known as proxy…
Masked conditional variational autoencoders for chromosome straightening
Jingxiong Li, Sunyi Zheng, Zhongyi Shui +9
Karyotyping is of importance for detecting chromosomal aberrations in human disease. However, chromosomes easily appear curved in microscopic images, which prevents cytogeneticists…
Understanding Overfitting in Adversarial Training via Kernel Regression
Teng Zhang, Kang Li
Adversarial training and data augmentation with noise are widely adopted techniques to enhance the performance of neural networks. This paper investigates adversarial training and…
AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer
Kang Li, Yan Song, Li-Rong Dai +3
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio t…