Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning

Overview

Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning

Update (September 18th, 2021)

A supporting document describing the difference between transfer learning, incremental learning, domain adaptation, and the proposed incremental cross-domain adaptation approach has been uploaded in this repository.

Update (August 15th, 2021)

Blind Testing Dataset has been released.

Introduction

This repository contains an implementation of the continual learning loss function (driven via Bayesian inference) to penalize the deep classification networks for incrementally learning the diverse ranging classification tasks across various domain shifts.

CL

Installation

To run the codebase, please download and install Anaconda (also install MATLAB R2020a with deep learning, image processing and computer vision toolboxes). Afterward, please import the ‘environment.yml’ or alternatively install following packages:

  1. Python 3.7.9
  2. TensorFlow 2.1.0 (CUDA compatible GPU needed for GPU training)
  3. Keras 2.3.0 or above
  4. OpenCV 4.2
  5. Imgaug 0.2.9 or above
  6. Tqdm
  7. Pandas
  8. Pillow 8.2.0

Both Linux and Windows OS are supported.

Datasets

The datasets used in the paper can be downloaded from the following URLs:

  1. Rabbani
  2. BIOMISA
  3. Zhang
  4. Duke-I
  5. Duke-II
  6. Duke-III
  7. Blind Testing Dataset

The datasets description file is also uploaded here. Moreover, please follow the same steps as mentioned below to prepare the training and testing data. These steps are also applicable for any custom dataset. Please note that in this research, the disease severity within the scans of all the above-mentioned datasets are marked by multiple expert ophthalmologists. These annotations are also released publicly in this repository.

Dataset Preparation

  1. Download the desired data and put the training images in '…\datasets\trainK' folder (where K indicates the iteration).
  2. The directory structure is given below:
├── datasets
│   ├── test
│   │   └── test_image_1.png
│   │   └── test_image_2.png
│   │   ...
│   │   └── test_image_n.png
│   ├── train1
│   │   └── train_image_1.png
│   │   └── train_image_2.png
│   │   ...
│   │   └── train_image_m.png
│   ├── train2
│   │   └── train_image_1.png
│   │   └── train_image_2.png
│   │   ...
│   │   └── train_image_j.png
│   ...
│   ├── trainK
│   │   └── train_image_1.png
│   │   └── train_image_2.png
│   │   ...
│   │   └── train_image_o.png

Training and Testing

  1. Use ‘trainer.py’ to train the chosen model incrementally. After each iteration, the learned representations are saved in a h5 file.
  2. After training the model instances, use ‘tester.py’ to generate the classification results.
  3. Use ‘confusionMatrix.m’ to view the obtained results.

Results

The detailed results of the proposed framework on all the above-mentioned datasets are stored in the 'results.mat' file.

Citation

If you use the proposed scheme (or any part of this code in your research), please cite the following paper:

@inproceedings{BayesianIDA,
  title   = {Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning},
  author  = {Taimur Hassan and Bilal Hassan and Muhammad Usman Akram and Shahrukh Hashmi and Abdul Hakeem and Naoufel Werghi},
  note = {IEEE Transactions on Instrumentation and Measurement},
  year = {2021}
}

Contact

If you have any query, please feel free to contact us at: [email protected].

Owner
Taimur Hassan
Taimur Hassan
codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification

DLCF-DCA codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification. submitted t

15 Aug 30, 2022
🛰️ Awesome Satellite Imagery Datasets

Awesome Satellite Imagery Datasets List of aerial and satellite imagery datasets with annotations for computer vision and deep learning. Newest datase

Christoph Rieke 3k Jan 03, 2023
Code-free deep segmentation for computational pathology

NoCodeSeg: Deep segmentation made easy! This is the official repository for the manuscript "Code-free development and deployment of deep segmentation

André Pedersen 26 Nov 23, 2022
ICCV2021 Paper: AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

ICCV2021 Paper: AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

Zongdai 107 Dec 20, 2022
Code for “ACE-HGNN: Adaptive Curvature ExplorationHyperbolic Graph Neural Network”

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network This repository is the implementation of ACE-HGNN in PyTorch. Environment pyt

9 Nov 28, 2022
An open source library for face detection in images. The face detection speed can reach 1000FPS.

libfacedetection This is an open source library for CNN-based face detection in images. The CNN model has been converted to static variables in C sour

Shiqi Yu 11.4k Dec 27, 2022
3D position tracking for soccer players with multi-camera videos

This repo contains a full pipeline to support 3D position tracking of soccer players, with multi-view calibrated moving/fixed video sequences as inputs.

Yuchang Jiang 72 Dec 27, 2022
Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

Learning to Simulate Dynamic Environments with GameGAN PyTorch code for GameGAN Learning to Simulate Dynamic Environments with GameGAN Seung Wook Kim,

199 Dec 26, 2022
Video Matting via Consistency-Regularized Graph Neural Networks

Video Matting via Consistency-Regularized Graph Neural Networks Project Page | Real Data | Paper Installation Our code has been tested on Python 3.7,

41 Dec 26, 2022
CS550 Machine Learning course project on CNN Detection.

CNN Detection (CS550 Machine Learning Project) Team Members (Tensor) : Yadava Kishore Chodipilli (11940310) Thashmitha BS (11941250) This is a work do

yaadava_kishore 2 Jan 30, 2022
Deep Learning for 3D Point Clouds: A Survey (IEEE TPAMI, 2020)

🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)

Qingyong 1.4k Jan 08, 2023
Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation.

Unified-EPT Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation. Installation Linux, CUDA=10.0,

29 Aug 23, 2022
A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

A tour through tensorflow with financial data I present several models ranging in complexity from simple regression to LSTM and policy networks. The s

195 Dec 07, 2022
Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021.

Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021. Figure 1: In the process of motion capture (mocap), some joints or even the whole human

Shinny cui 3 Oct 31, 2022
Understanding Convolution for Semantic Segmentation

TuSimple-DUC by Panqu Wang, Pengfei Chen, Ye Yuan, Ding Liu, Zehua Huang, Xiaodi Hou, and Garrison Cottrell. Introduction This repository is for Under

TuSimple 585 Dec 31, 2022
[CVPR 2021 Oral] ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis [arxiv|pdf|v

Yinan He 78 Dec 22, 2022
Unofficial implement with paper SpeakerGAN: Speaker identification with conditional generative adversarial network

Introduction This repository is about paper SpeakerGAN , and is unofficially implemented by Mingming Huang ( 7 Jan 03, 2023

Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

SSL_OSC Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

zaixizhang 2 May 14, 2022
Data for "Driving the Herd: Search Engines as Content Influencers" paper

herding_data Data for "Driving the Herd: Search Engines as Content Influencers" paper Dataset description The collection contains 2250 documents, 30 i

0 Aug 17, 2021
[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora

VITA 64 Dec 08, 2022