Topology Aware Delineation

Final Project for M2 MVA course: Deformable models and geodesic methods for image analysis. In this project, we implement and analyse the method proposed in Beyond the Pixel-Wise Loss for Topology-Aware Delineation using PyTorch. It aims to improve the performance for the problem of delineation of curvilinear structures using deep learning methods.

Figure 1: Training Pipeline Reprinted from Article

Requirements

PyTorch 1.0
>= Python 3
Visdom

Dataset

We test our algorithm on Massachusetts Roads Dataset. A Python script is provided in the Data folder to download the whole dataset. We then resize all images to 256 in order to reduce memory usage.

Run

Training

First we train a UNet-based model with topology-aware loss using K=1.

python -m visdom.server 
python train.py

Then the model is finetuned using K=3 on the same dataset.

python train.py --K 3 --model ../log/pretrained/model.t7

Testing

python test.py --model path_to_model --image path_to_image --label path_to_groundtruth

Results

We provide three pretrained models in the log folder, namely the UNet model without topology-aware loss (pure UNet), the UNet model with topology-aware loss using K=1 (Topological UNet), and the finetuned UNet model with topology-aware loss using K=3 (Iterative UNet).