-
RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Imag...
Fine-grained image recognition (FGIR) has been a challenging problem. Most of the current methods are dominated by convolutional neural networks (CNNs). FGIR has the problem of... -
Region Attention Transformer for Medical Image Restoration
The proposed region attention transformer (RAT) for medical image restoration, which conducts attention within similar semantic regions, facilitating pixels with similar...