From d94446fb9aef4a32bc2fac9cbd628e3af18701b9 Mon Sep 17 00:00:00 2001 From: pascalcpp <1287971058@qq.com> Date: Tue, 12 Nov 2024 21:36:28 +0800 Subject: [PATCH 1/6] Update README.md --- README.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index abb8463..15745ec 100644 --- a/README.md +++ b/README.md @@ -26,10 +26,11 @@ the current State-of-the-Art (SOTA) methods by 2.57%, 3.04%, and 2.34% in the Di ## Introduction Official code for "SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation". -Due to the large size of the model parameter files, it is difficult to upload them anonymously. After our paper is accepted, we will publish both the pretrained model and the fully trained model. The proof for the kl_loss in the code can be found in the document "MICCAI2024_SDCL.pdf". - +## News +2024/11/12 +We provide SDCL model parameters [google drive](https://drive.google.com/file/d/18C5C8VEUnFFZwg-zG6pu1WPC0Bi3GLCe/view?usp=drive_link). ## Requirements This repository is based on PyTorch 2.1.0, CUDA 12.1, and Python 3.8. All experiments in our paper were conducted on an NVIDIA GeForce RTX 4090 GPU with an identical experimental setting under Windows. ## Datasets From f39f8fd206beab992c9c5b4f771835c062acd562 Mon Sep 17 00:00:00 2001 From: pascalcpp <1287971058@qq.com> Date: Tue, 12 Nov 2024 21:44:47 +0800 Subject: [PATCH 2/6] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 15745ec..bdf5541 100644 --- a/README.md +++ b/README.md @@ -30,7 +30,7 @@ Official code for "SDCL: Students Discrepancy-Informed Correction Learning for S The proof for the kl_loss in the code can be found in the document "MICCAI2024_SDCL.pdf". ## News 2024/11/12 -We provide SDCL model parameters [google drive](https://drive.google.com/file/d/18C5C8VEUnFFZwg-zG6pu1WPC0Bi3GLCe/view?usp=drive_link). +We provide SDCL model parameters [google drive](https://drive.google.com/file/d/18C5C8VEUnFFZwg-zG6pu1WPC0Bi3GLCe/view?usp=sharing). ## Requirements This repository is based on PyTorch 2.1.0, CUDA 12.1, and Python 3.8. All experiments in our paper were conducted on an NVIDIA GeForce RTX 4090 GPU with an identical experimental setting under Windows. ## Datasets From 85d4aa280968be57265818f3eb962d3efe4912dd Mon Sep 17 00:00:00 2001 From: pascalcpp <1287971058@qq.com> Date: Tue, 12 Nov 2024 21:45:44 +0800 Subject: [PATCH 3/6] Update README.md --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index bdf5541..47e222f 100644 --- a/README.md +++ b/README.md @@ -29,7 +29,8 @@ Official code for "SDCL: Students Discrepancy-Informed Correction Learning for S The proof for the kl_loss in the code can be found in the document "MICCAI2024_SDCL.pdf". ## News -2024/11/12 +2024/11/12 + We provide SDCL model parameters [google drive](https://drive.google.com/file/d/18C5C8VEUnFFZwg-zG6pu1WPC0Bi3GLCe/view?usp=sharing). ## Requirements This repository is based on PyTorch 2.1.0, CUDA 12.1, and Python 3.8. All experiments in our paper were conducted on an NVIDIA GeForce RTX 4090 GPU with an identical experimental setting under Windows. From cfb260f695148a2967d7faf7332429e8c21b73b8 Mon Sep 17 00:00:00 2001 From: pascalcpp <1287971058@qq.com> Date: Mon, 18 Nov 2024 03:04:52 +0800 Subject: [PATCH 4/6] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 47e222f..08ff522 100644 --- a/README.md +++ b/README.md @@ -31,7 +31,7 @@ The proof for the kl_loss in the code can be found in the document "MICCAI2024_S ## News 2024/11/12 -We provide SDCL model parameters [google drive](https://drive.google.com/file/d/18C5C8VEUnFFZwg-zG6pu1WPC0Bi3GLCe/view?usp=sharing). +We provide SDCL model weights [google drive](https://drive.google.com/file/d/18C5C8VEUnFFZwg-zG6pu1WPC0Bi3GLCe/view?usp=sharing). ## Requirements This repository is based on PyTorch 2.1.0, CUDA 12.1, and Python 3.8. All experiments in our paper were conducted on an NVIDIA GeForce RTX 4090 GPU with an identical experimental setting under Windows. ## Datasets From e8d5c1a998abfc73365166611b52e5ac232319bb Mon Sep 17 00:00:00 2001 From: pascalcpp <1287971058@qq.com> Date: Sat, 21 Mar 2026 15:32:02 +0800 Subject: [PATCH 5/6] Update README.md --- README.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/README.md b/README.md index 08ff522..592226b 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,6 @@ - # SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation + # SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation (MICCAI 2024) #### By [Bentao Song](), [Qingfeng Wang]() - -![MICCAI2024](https://img.shields.io/badge/MICCAI-2024-blue) Pytorch implementation of our method for MICCAI 2024 paper: "SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation".[Paper Link](https://papers.miccai.org/miccai-2024/672-Paper0821.html) ## Contents From 63d701f8fdd1b2ed0b7be2495f35437eeae91ad4 Mon Sep 17 00:00:00 2001 From: pascalcpp <1287971058@qq.com> Date: Sat, 21 Mar 2026 15:37:15 +0800 Subject: [PATCH 6/6] Update README.md --- README.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/README.md b/README.md index 592226b..6570963 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,5 @@ # SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation (MICCAI 2024) - #### By [Bentao Song](), [Qingfeng Wang]() - Pytorch implementation of our method for MICCAI 2024 paper: "SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation".[Paper Link](https://papers.miccai.org/miccai-2024/672-Paper0821.html) ## Contents - [Abstract](##Abstract) @@ -68,7 +66,7 @@ If our SDCL is useful for your research, please consider citing: organization={Springer} } ## Acknowledgements -Our code is largely based on [BCP](https://github.com/DeepMed-Lab-ECNU/BCP). Thanks for these authors for their valuable work, hope our work can also contribute to related research. +Our code is largely based on [BCP](https://github.com/DeepMed-Lab-ECNU/BCP) and [SSL4MIS](https://github.com/HiLab-git/SSL4MIS). Thanks for these authors for their valuable work, hope our work can also contribute to related research.