2 papers
cs.CV2024
SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
Nick Nikzad, Yi Liao, Yongsheng Gao +1
Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance thei…
cs.CV2024
CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks
Nick Nikzad, Yongsheng Gao, Jun Zhou
In recent years, convolutional neural networks (CNNs) with channel-wise feature refining mechanisms have brought noticeable benefits to modelling channel dependencies. However, cur…