Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on Medical Image Segmentation

no code implementations • 28 Nov 2022 • Shaolei Liu, Siqi Yin, Linhao Qu, Manning Wang

Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain.

Image Segmentation Medical Image Segmentation +2

Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)

1 code implementation • 9 Nov 2022 • Kexue Fu, Jiazheng Luo, Xiaoyuan Luo, Shaolei Liu, Chenxi Zhang, Manning Wang

In this paper, we propose a novel deep graph matching-based framework for point cloud registration.

graph construction Graph Matching +1

DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification

1 code implementation • 17 Jun 2022 • Linhao Qu, Xiaoyuan Luo, Shaolei Liu, Manning Wang, Zhijian Song

Multiple Instance Learning (MIL) is widely used in analyzing histopathological Whole Slide Images (WSIs).

Classification Image Classification +3

POS-BERT: Point Cloud One-Stage BERT Pre-Training

1 code implementation • 3 Apr 2022 • Kexue Fu, Peng Gao, Shaolei Liu, Renrui Zhang, Yu Qiao, Manning Wang

We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process.

Contrastive Learning Language Modelling +3

TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning

no code implementations • 19 Jan 2022 • Linhao Qu, Shaolei Liu, Manning Wang, Shiman Li, Siqi Yin, Qin Qiao, Zhijian Song

In order to encourage different fusion tasks to promote each other and increase the generalizability of the trained network, we integrate the three self-supervised auxiliary tasks by randomly choosing one of them to destroy a natural image in model training.

Multi-Exposure Image Fusion Self-Supervised Learning

TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning

2 code implementations • 2 Dec 2021 • Linhao Qu, Shaolei Liu, Manning Wang, Zhijian Song

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning.

Multi-Exposure Image Fusion Multi-Task Learning

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

no code implementations • 12 Apr 2021 • Xiaoyuan Luo, Shaolei Liu, Kexue Fu, Manning Wang, Zhijian Song

In the UDA architecture, an encoder is shared between the networks for the self-supervised task and the main task of point cloud classification or segmentation, so that the encoder can be trained to extract features suitable for both the source and the target domain data.

Point Cloud Classification Self-Supervised Learning +1

Robust Point Cloud Registration Framework Based on Deep Graph Matching

2 code implementations • CVPR 2021 • Kexue Fu, Shaolei Liu, Xiaoyuan Luo, Manning Wang

In this paper, we propose a novel deep graph matchingbased framework for point cloud registration.

graph construction Graph Matching +1

WaveFuse: A Unified Deep Framework for Image Fusion with Discrete Wavelet Transform

1 code implementation • 28 Jul 2020 • Shaolei Liu, Manning Wang, Zhijian Song

We propose an unsupervised image fusion architecture for multiple application scenarios based on the combination of multi-scale discrete wavelet transform through regional energy and deep learning.