24 citations · 37 across the 5 of their papers we have counts for
6 papers
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
Xiuchao Sui, Shaohua Li, Xue Geng +5
Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow…
Few-Shot Domain Adaptation with Polymorphic Transformers
Shaohua Li, Xiuchao Sui, Jie Fu +7
Deep neural networks (DNNs) trained on one set of medical images often experience severe performance drop on unseen test images, due to various domain discrepancy between the train…
Medical Image Segmentation Using Squeeze-and-Expansion Transformers
Shaohua Li, Xiuchao Sui, Xiangde Luo +3
Medical image segmentation is important for computer-aided diagnosis. Good segmentation demands the model to see the big picture and fine details simultaneously, i.e., to learn ima…
Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
Shaohua Li, Xiuchao Sui, Jie Fu +2
Convolutional Neural Networks (CNNs) are known to be brittle under various image transformations, including rotations, scalings, and changes of lighting conditions. We observe that…
RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer and Time-efficient Path Optimization
Tianying Wang, Wei Qi Toh, Hao Zhang +4
Robotic drawing has become increasingly popular as an entertainment and interactive tool. In this paper we present RoboCoDraw, a real-time collaborative robot-based drawing system…
Multi-Instance Multi-Scale CNN for Medical Image Classification
Shaohua Li, Yong Liu, Xiuchao Sui +4
Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs)…