Topology-Preserving Downsampling of Binary Images, ECCV2024

Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch

A resource repository for 3D machine learning

Retinal Vessel Segmentation using U-Net architecture. DRIVE and STARE datasets are used.

Retina blood vessel segmentation with a convolutional neural network

Code for the MICCAI 2024 paper "HyperSpace: Hypernetworks for spacing-adaptive image segmentation"

Fast Implementation of Generalised Geodesic Distance Transform for CPU (OpenMP) and GPU (CUDA)

An tiny example for the implementation of a custom plugin in ImFusionSuite

Cut and paste augmentation for object detection and instance segmentation

A curated list of topological data analysis (TDA) resources and links.

In this repository you can see the code for skeletonization of binary images using our novel fuzzy inference system.

MALIS structured loss function for supervised learning of segmentation and clustering

Reimplementation of "A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology".

PyTorch Implementation of XNOR-Net

Official code for "Boundary loss for highly unbalanced segmentation", runner-up for best paper award at MIDL 2019. Extended version in MedIA, volume 67, January 2021.

[IEEE JBHI, 2023] Towards Connectivity-Aware Pulmonary Airway Segmentation

Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm. In ECCV 2018 and IJCV

Pytorch implementation of our paper accepted by ICCV 2021 -- ReCU: Reviving the Dead Weights in Binary Neural Networks https://arxiv.org/abs/2103.12369

BMXNet 2: An Open-Source Binary Neural Network Implementation Based on MXNet

Pytorch implementation of our paper accepted by TPAMI 2022 -- SiMaN: Sign-to-Magnitude Network Binarization

Spatial Decomposition and Transformation Network - TensorFlow

Decoupled Weight Decay Regularization (ICLR 2019)

Sampling profiler for Python programs

Memray is a memory profiler for Python

A Library for Differentiable Logic Gate Networks