deep learning
paper summary “Perceiver IO: A General Architecture for Structured Inputs & Outputs”
arxiv: https://arxiv.org/abs/2107.14795 Key points developing upon the Perceiver idea, Perceiver IO proposes a Perceiver like structure but where output size can be much larger and still keep overall complexity linear. (Checkout summary on Perceiver here) same with Perceiver, Read more…
deep learning
paper summary: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
arxiv: https://arxiv.org/abs/2103.14030 Key points multi scale feature extraction. Could think of as adoption of FPN idea. restrict transformer operation to within each window and not the entire feature map → allows to keep overall complexity linear Read more…