prinshul Goto Github PK

active-bayesian-causal-inference

Active Bayesian Causal Inference (Neurips'22)

adaptive-distribution-calibration-for-few-shot-learning-with-hierarchical-optimal-transport

adelaidet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

algos

Algorithms

alphatensor

analyse-voting-patterns-using-polytomous-latent-class-analysis-polca-clustering

Examine the voting patterns of members(TD’s) of different parties. The 166 Members of Dail Éireann, called Teachtaí Dála (TDs) Between January 14th 2016 and January 21st 2016 inclusive there were 6 votes ED1, ED2, Credit, Confidence1, Confidence2, Trade. The data records, if a TD was absent for a vote (coded 1) or voted no (coded 2) or voted yes (coded 3) Polytomous Latent class analysis is a statistical technique for the analysis of multivariate categorical data. It is a finite mixture model that uses Expectation Maximization algorithm poLCA estimates the latent class model by maximizing the log-likelihood function Bayesian Information Criteria (BIC) is used to locate the best fitting model. Implemented in R

awesome-action-recognition

A curated list of action recognition and related area resources

awesome-diffusion-models

A collection of resources and papers on Diffusion Models

awesome-domain-adaptation

A collection of AWESOME things about domian adaptation

awesome-self-supervised-learning

A curated list of awesome self-supervised methods

awesome-transformer-attention

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

causalbayesianoptimization

Code for the Causal Bayesian Optimization algorithm (http://proceedings.mlr.press/v108/aglietti20a/aglietti20a.pdf)

cbed

Official implementation of the paper "Interventions, Where and How? Experimental Design for Causal Models at Scale", NeurIPS 2022.

clcc-semi

ISBI 2022: Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image Segmentation.

clustering-of-genetics-data

Human Genome Diversity Project, a large collection of genomes from around the world Build a model to cluster human individuals into groups based on genetic information. Genetic data can be represented as vectors of 0s, 1s, and 2s for each individual. 2 indicates the individual has two copies of the reference allele. 0 indicates the individual has inherited two copies of the alternate allele and 1 indicates the individual inherited an alternate allele from one parent and a reference allele from the other. Genotype data X where xnm is the genotype of individual n at marker m. N = 172 individuals (from 8 different sub-populations) at M = 64 markers. Likelihood for data is a Binomial distribution Unknown parameters are cluster memberships for the individuals, Z; a vector of length N taking values 1, 2, ., K and cluster specific frequencies at each marker, F; a K × M matrix of values that lie between 0 and 1. Flat categorical and beta priors are assumed. Perform Bayesian inference on the cluster memberships of each individual and on the frequency of mutations within each cluster at each marker. Sample from posterior for Z and F Use Deviance Information Criterion (DIC) to find best K Implemented in JAGS/R

contrastive-learning-with-non-semantic-negatives

Robust Contrastive Learning Using Negative Samples with Diminished Semantics (NeurIPS 2021)

data-collection-preparation

The objective of this project is to collect a dataset from one or more open web APIs of your choice, and use Python to pre-process and analyse the collected data. 1. Choose one or more open web APIs as your source of data. If you decide to use more than one API, the APIs should be related in some way. 2. Collect data from your chosen API(s) using Python. Your dataset should contain at least 100 records/items in total. Depending on the API(s), you may need to repeat the collection process multiple times to download sufficient data. 3. Parse the collected data, and store it in an appropriate file format for subsequent analysis (e.g. plain text, JSON, XML, CSV). 4. Load and represent the data using an appropriate data structure (i.e. records/ items as rows, described by features as columns). Apply any pre-processing steps that might be required to clean/filter/combine the data before analysis. 5. Analyse and summarize the cleaned dataset, using tables and visualizations where appropriate.

ddm

ddm2

Official repository of DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models, ICLR2023

deep-kernel-transfer

Official pytorch implementation of the paper "Deep Kernel Transfer in Gaussian Processes for Few-shot Learning"

detco

diffusionmbir

Official PyTorch implementation of the CVPR 2023 paper "Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models (https://arxiv.org/abs/2211.10655)"

dispr

A Diffusion Model Predicts 3D Shapes from 2D Microscopy Images

few-shot-semantic-segmentation-papers

Few Shot Semantic Segmentation Papers

generative-learning

Code for Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping

gfm-plus

[ICML 2023] Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization.

glss

glss-1

Code for the paper 'Skin Segmentation from NIR Images using Unsupervised Domain Adaptation through Generative Latent Search'. Accepted in ECCV2020 (Spotlight). Preprint: https://arxiv.org/abs/2006.08696

google-research

Google Research

gwsdr