The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NIPS 2020.

Last update: Dec 28, 2022

Related tags

Overview

Domain Generalization for Medical Imaging Classification with Linear Dependency Regularization

The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NeurIPS 2020. The pre-print paper can be found in Arxiv.

How to use

First, you need to install the package surface-distance https://github.com/deepmind/surface-distance and SimpleITK

pip install SimpleITK

Then run the following command to train and evaluate the performance of the model

python3 train_lddg.py -t i

where i means set_i is the target domain.

Segmentation Reuslts

Please cite our paper if you find it's useful.

@article{li2020domain, title={Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization}, author={Li, Haoliang and Wang, YuFei and Wan, Renjie and Wang, Shiqi and Li, Tie-Qiang and Kot, Alex C}, journal={arXiv preprint arXiv:2009.12829}, year={2020} }

Comments

Proof for Theorem 2

Hi, thank you for your great paper. I'm sorry that I can't understand parts of the proof for theorem 2.

(1) Here you assume L() denotes the cross-entropy loss with softmax operation. Does that mean y is the input of the softmax function? Because only in this case the linear relation between the target y and the source y's holds.

(2) I'm also confused how you derive from the first line to the second line (including how you take the sum over j outside of the loss function and how you change p* to pj).

(3) What's more, you said you used the upper bound of log-sum-exp function to derive the second line. And {a1, a2, ..., an} are the outputs of the softmax function. Then I'm not sure where the exponential comes in the log-sum-exp function that takes the exponential of a.

Thank you for your kind reply.

opened by cnyanhao 1
The code for skin lesion classification

Hi, I find this repo only has the code for spinal cord gray matter segmentation. Is there any plan to release the code for skin lesion classification in the future?

opened by BurningFr 1
Code problem

In https://github.com/wyf0912/LDDG/blob/0242b2b739953a3545c954b5487f58600e981692/train_lddg.py#L164 why only use fisrt 2000 features, not all ? just to reduce compuation ?

opened by SakurajimaMaiii 0
low_rank_loss_spinal

first of all, I would like to thank you for your great work. I have some doubts about your code, can you please reply to me with the following request: why did you set the latent_dim= 8 ?, why did you take the svd from the first 2000 elements of the features matrix and why did you choose the low_rank_loss_spinal=S_spinal[2]?

opened by DrraBL 0
Spinal Cord Challenge Dataset

Hello! Your work is great and impressive, but now I encounter a problem with the downloading of Spinal Cord Challenge Dataset. Could you please tell me how to get this dataset? Thanks very much.

opened by FaceCold 3

The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NIPS 2020.

Related tags

Overview

Domain Generalization for Medical Imaging Classification with Linear Dependency Regularization

How to use

Segmentation Reuslts

Please cite our paper if you find it's useful.

Comments

Proof for Theorem 2

The code for skin lesion classification

Code problem

low_rank_loss_spinal

Spinal Cord Challenge Dataset

Owner

Yufei Wang

[CVPR'21] FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space

Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization

Adaout is a practical and flexible regularization method with high generalization and interpretability

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path

Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)

Official pytorch implementation of "Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization" ACMMM 2021 (Oral)

Implementation for "Domain-Specific Bias Filtering for Single Labeled Domain Generalization"

A medical imaging framework for Pytorch

Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

Official Keras Implementation for UNet++ in IEEE Transactions on Medical Imaging and DLMIA 2018

Official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"

Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks

IJCAI2020 & IJCV 2020 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation"

Official implementation of paper Gradient Matching for Domain Generalization

The official repository for paper ''Domain Generalization for Vision-based Driving Trajectory Generation'' submitted to ICRA 2022