A Versatile Backbone for Dense Prediction without Convolutions
This repository contains PyTorch evaluation code, training code and pretrained models for PVT (Pyramid Vision Transformer).
A modular architecture that decouples a task into visual perception and action policy
MOCA (Modular Object-Centric Approach) is a modular architecture that decouples a task into visual perception and action policy.
AutoML for Renewable Energy Industries
The GreenGuard project is a collection of end-to-end solutions for machine learning problems commonly found in monitoring wind energy production systems.
A simple abstraction layer in Python for building knowledge graphs
The kglab library provides a simple abstraction layer in Python for building knowledge graphs.
A polimorfic optimization framework for Fluorescence Microscopy based on Pytorch
Optimization framework developed in Pytorch, allowing calibration, and joint optimization of optics and deep learning models.
A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation
The code for DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation.
An extremely easy improvement of Batch Normalization
We present Sandwich Batch Normalization (SaBN), an extremely easy improvement of Batch Normalization (BN) with only a few lines of code changes.
Version control for machine learning
Keepsake is a Python library that uploads files and metadata (like hyperparameters) to Amazon S3 or Google Cloud Storage.
Transfer SemanticKITTI labeles into other dataset/sensor formats
Code for Langer et al. "Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks", IROS, 2020.
An open source framework for research in Embodied-AI from AI2
AllenAct is a modular and flexible learning framework designed with a focus on the unique requirements of Embodied-AI research.
Neovim plugin to open multiple files in one buffer
monolithic.nvim allows you to open multiple files in one buffer.
Probabilistic ODE Solvers via Bayesian Filtering and Smoothing
ProbNumDiffEq.jl provides probabilistic ODE solvers for the DifferentialEquations.jl ecosystem.
Python toolbox to evaluate graph vulnerability and robustness
TIGER is a Python toolbox to conduct graph vulnerability and robustness research.
A Parametric Surface Fitting Network for 3D Point Clouds
This repository contains codebase for the ParSeNet paper published at ECCV-2020.
Instance Localization for Self-supervised Detection Pretraining
[arXiv 2021] Instance Localization for Self-supervised Detection Pretraining.
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks
Official PyTorch implementation of "Joint Object Detection and Multi-Object Tracking with Graph Neural Networks"
Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
Implementation for EMNLP-2020 paper: Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product.
An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
Open source code for EMNLP 2020 Findings Paper "AGIF: An Adaptive Graph-Interactive Framework for Joint MultipleIntent Detection and Slot Filling"
Weakly Supervised Learning of Rigid 3D Scene Flow
This repository provides code and data to train and evaluate a weakly supervised method for rigid 3D scene flow estimation.
Semi-Supervised Classification via Annealed Self-Training
Self-training is a standard approach to semi-supervised learning where the learner's own predictions on unlabeled data are used as supervision during training.