Nalan Karunanayake's repositories
awesome-computational-neuroscience
A list of schools and researchers in computational neuroscience
BUS-GAN
Semi-supervised Segmentation of Tumors from Breast Ultrasound Images with Attentional Generative Adversarial Network
CNN-BUS-segment
Convolutional neural networks for semantic segmentation of tumors in breast ultrasound images
dataset-uta4-dicom
:bar_chart: [AVI 2020] UTA4: Medical Imaging DICOM Files Dataset
datasharing
The Leek group guide to data sharing
defgrid-release
Official PyTorch implementation of Deformable Grid (ECCV 2020)
Dynamics_In_Neuro_Lectures_2021
A set of lectures I gave for Chris Rozell's "Information Processing Models in Neural Systems" course at Georgia Insitute of Technology
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
generative-compression
TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression
Guided-Bilateral-Filter-based-Medical-Image-Fusion-Using-Visual-Saliency-Map-in-the-Wavelet-Domain
Guided-Bilateral Filter-based Medical Image Fusion Using Visual Saliency Map in the Wavelet Domain
image-compression-kmeans
Image compression using K-Means.
ITSRio-TCC
ITSRio TCC (Trabalho de Conclusão de Curso) - Computação
MAgent
A Platform for Many-agent Reinforcement Learning
ML-Course-Notes
🎓 Sharing course notes on all topics related to machine learning, NLP, and AI.
MOOC-neurons-and-synapses-2017
Reference data for the "Simulation Neuroscience:Neurons and Synapses" Massive Online Open Course
NeuroM
Neuronal Morphology Analysis Tool
NEURONexercises-nalan-bnni
Repository of exercises using the NEURON simulator
NN-SVG
Publication-ready NN-architecture schematics.
opencv
Open Source Computer Vision Library
orientation-field-control
Matlab code for orientation field control based on PVFC
pypc
Predictive coding in Python
superpixel-benchmark
An extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.
texSeg
Weakly-Supervised Sparse Coding With Geometric Prior for Interactive Texture Segmentation-SPL 2019 Texture segmentation is about dividing a texturedominant image into multiple homogeneous texture regions. The existing unsupervised approaches for texture segmentation are annotation-free but often yield unsatisfactory results. In contrast, supervised approaches such as deep learning may have better performance but require a large amount of annotated data. In this letter, we propose a user-interactive approach to win the trade-off between unsupervised approaches and supervised deep approaches. Our approach requires the user to mark one pixel in each texture region, whose label is directly propagated to its neighbor region. Such labeled data are of very small amount and even partially erroneous. To effectively exploit such weakly-labeled data, we construct a weakly-supervised sparse coding model that jointly conducts feature learning and segmentation. In addition, the geometric constraints are developed for the model to exploit the geometric prior on the local connectivity of region boundaries. The experiments on two benchmark datasets have validated the effectiveness of the proposed approach.
U-2-Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."