Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

Overview

CRF - Conditional Random Fields

A library for dense conditional random fields (CRFs).

This is the official accompanying code for the paper Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond published at NeurIPS 2021 by Đ.Khuê Lê-Huu and Karteek Alahari. Please cite this paper if you use any part of this code, using the following BibTeX entry:

@inproceedings{lehuu2021regularizedFW,
  title={Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond},
  author={L\^e-Huu, \DJ.Khu\^e and Alahari, Karteek},
  booktitle={Neural Information Processing Systems (NeurIPS)},
  year={2021}
}

Currently the code is messy and undocumented, and we apology for that. We will make an effort to fix this soon. To facilitate the maintenance, the code and pre-trained models for the semantic segmentation task will be available in a separate repository.

Installation

git clone https://github.com/netw0rkf10w/CRF.git
cd CRF
python setup.py install

Usage

After having installed the package, you can create a CRF layer as follows:

import CRF

params = CRF.FrankWolfeParams(scheme='fixed', # constant stepsize
            stepsize=1.0,
            regularizer='l2',
            lambda_=1.0, # regularization weight
            lambda_learnable=False,
            x0_weight=0.5, # useful for training, set to 0 if inference only
            x0_weight_learnable=False)

crf = CRF.DenseGaussianCRF(classes=21,
                alpha=160,
                beta=0.05,
                gamma=3.0,
                spatial_weight=1.0,
                bilateral_weight=1.0,
                compatibility=1.0,
                init='potts',
                solver='fw',
                iterations=5,
                params=params)

Detailed documentation on the available options will be added later.

Below is an example of how to use this layer in combination with a CNN. We can define for example the following simple CNN-CRF module:

import torch

class CNNCRF(torch.nn.Module):
    """
    Simple CNN-CRF model
    """
    def __init__(self, cnn, crf):
        super().__init__()
        self.cnn = cnn
        self.crf = crf

    def forward(self, x):
        """
        x is a batch of input images
        """
        logits = self.cnn(x)
        logits = self.crf(x, logits)
        return logits

# Create a CNN-CRF model from given `cnn` and `crf`
# This is a PyTorch module that can be used in a usual way
model = CNNCRF(cnn, crf)

Acknowledgements

The CUDA implementation of the permutohedral lattice is due to https://github.com/MiguelMonteiro/permutohedral_lattice. An initial version of our permutohedral layer was based on https://github.com/Fettpet/pytorch-crfasrnn.

Owner
Đ.Khuê Lê-Huu
Đ.Khuê Lê-Huu
This is the latest version of the PULP SDK

PULP-SDK This is the latest version of the PULP SDK, which is under active development. The previous (now legacy) version, which is no longer supporte

78 Dec 07, 2022
Torchreid: Deep learning person re-identification in PyTorch.

Torchreid Torchreid is a library for deep-learning person re-identification, written in PyTorch. It features: multi-GPU training support both image- a

Kaiyang 3.7k Jan 05, 2023
[CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

TBE The source code for our paper "Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Le

Jinpeng Wang 150 Dec 28, 2022
A crossplatform menu bar application using mpv as DLNA Media Renderer.

Macast Chinese README A menu bar application using mpv as DLNA Media Renderer. Install MacOS || Windows || Debian Download link: Macast release latest

4.4k Jan 01, 2023
Linear image-to-image translation

Linear (Un)supervised Image-to-Image Translation Examples for linear orthogonal transformations in PCA domain, learned without pairing supervision. Tr

Eitan Richardson 40 Aug 31, 2022
BasicRL: easy and fundamental codes for deep reinforcement learning。It is an improvement on rainbow-is-all-you-need and OpenAI Spinning Up.

BasicRL: easy and fundamental codes for deep reinforcement learning BasicRL is an improvement on rainbow-is-all-you-need and OpenAI Spinning Up. It is

RayYoh 12 Apr 28, 2022
Official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence".

The DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergen

281 Dec 30, 2022
This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

BiPointNet: Binary Neural Network for Point Clouds Created by Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Li

Haotong Qin 59 Dec 17, 2022
Official implementation for Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

1 SNAS4MTF This repo is the official implementation for Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting. 1.1 The frame

SZJ 5 Sep 21, 2022
Multi Agent Reinforcement Learning for ROS in 2D Simulation Environments

IROS21 information To test the code and reproduce the experiments, follow the installation steps in Installation.md. Afterwards, follow the steps in E

11 Oct 29, 2022
Unsupervised Image to Image Translation with Generative Adversarial Networks

Unsupervised Image to Image Translation with Generative Adversarial Networks Paper: Unsupervised Image to Image Translation with Generative Adversaria

Hao 71 Oct 30, 2022
Long Expressive Memory (LEM)

Long Expressive Memory for Sequence Modeling This repository contains the implementation to reproduce the numerical experiments of the paper Long Expr

Konstantin Rusch 47 Dec 17, 2022
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

This repository holds NVIDIA-maintained utilities to streamline mixed precision and distributed training in Pytorch. Some of the code here will be included in upstream Pytorch eventually. The intenti

NVIDIA Corporation 6.9k Jan 03, 2023
Real time sign language recognition

The proposed work aims at converting american sign language gestures into English that can be understood by everyone in real time.

Mohit Kaushik 6 Jun 13, 2022
This app is a simple example of using Strealit to create a financial data web app.

Streamlit Demo: Finance Chart This app is a simple example of using Streamlit to create a financial data web app. This demo use streamlit, pandas and

91 Jan 02, 2023
Learned model to estimate number of distinct values (NDV) of a population using a small sample.

Learned NDV estimator Learned model to estimate number of distinct values (NDV) of a population using a small sample. The model approximates the maxim

2 Nov 21, 2022
Explaining neural decisions contrastively to alternative decisions.

Contrastive Explanations for Model Interpretability This is the repository for the paper "Contrastive Explanations for Model Interpretability", about

AI2 16 Oct 16, 2022
Beancount-mercury - Beancount importer for Mercury Startup Checking

beancount-mercury beancount-mercury provides an Importer for converting CSV expo

Michael Lynch 4 Oct 31, 2022
A really easy-to-use and powerful sudoku solver.

SodukuSolver This is a really useful sudoku solver with a Qt gui. USAGE Enter the numbers in and click "RUN"! If you don't want to wait, simply press

Ujhhgtg Teams 11 Jun 02, 2022
Addition of pseudotorsion caclulation eta, theta, eta', and theta' to barnaba package

Addition to Original Barnaba Code: This is modified version of Barnaba package to calculate RNA pseudotorsion angles eta, theta, eta', and theta'. Ple

Mandar Kulkarni 1 Jan 11, 2022