research
∙
03/31/2022
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
Optical flow estimation aims to find the 2D motion field by identifying ...
share
research
∙
07/10/2021
Few-Shot Domain Adaptation with Polymorphic Transformers
Deep neural networks (DNNs) trained on one set of medical images often e...
research
∙
05/20/2021
Medical Image Segmentation using Squeeze-and-Expansion Transformers
Medical image segmentation is important for computer-aided diagnosis. Go...
research
∙
04/12/2020
Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
Convolutional Neural Networks (CNNs) are known to be brittle under vario...
research
∙
07/04/2019