You Hao

TL;DR: This letter presents a kind of network architecture to introduce AMI into CNN, which is called AMI-Net, and achieves this by calculating AMI on the feature maps of the hidden layers to extend the dimension of AMIs and introduce affine transformation invariant into CNN.

TL;DR: In this paper, an Affine-Gradient based Local Binary Pattern (AGLBP) descriptor was proposed for texture classification. But it is difficult to describe complicated texture using single type information, such as Local Binary Patterns (LBP), which just utilizes the sign information of the difference between pixel and its local neighbors.

TL;DR: An approach for learning a single model that universally segments 33 anatomical structures, including vertebrae, pelvic bones, and abdominal organs is presented, and a cross-patch transformer module is proposed to fuse more information in adjacent patches, which enlarges the aggregated receptive field for improved segmentation performance.

TL;DR: The experiments show that the five chirality invariants are effective and efficient, they can be used as a tool for symmetry detection or features in shape analysis and give a geometric view to study the chiral invariants.