Building blocks for uncertainty-aware cycle consistency presented at NeurIPS'21.

Overview

UncertaintyAwareCycleConsistency

This repository provides the building blocks and the API for the work presented in the NeurIPS'21 paper Robustness via Uncertainty-aware Cycle Consistency. Translation methods often learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty, leading to performance degradation when encountering unseen perturbations at test time. To address this, we propose a method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by generalized Gaussian distribution, capable of modelling heavy-tailed distributions.

Requirements

python >= 3.6.10
pytorch >= 1.6.0
jupyter lab
torchio
scikit-image
scikit-learn

The structure of the repository is as follows:

root
 |-ckpt/ (will save all the checkpoints)
 |-data/ (save your data and related script)
 |-src/ (contains all the source code)
    |-ds.py 
    |-networks.py
    |-utils.py
    |-losses.py

Preparing Datasets

To prepare your datasets to use with this repo, place the root directory of the dataset in data/. The recommended way to structure your data is shown below.

data/
    |-Dataset_1/
        |-A/
            |-image1.png
            |-image2.png
            |-image3.png
            |-...
        |-B/
            |-image1.png
            |-image2.png
            |-image3.png
            |-...

Note the images need not be paired. The python script src/ds.py provides the PyTorch Dataset class to read such a dataset, used as explained below.

class Images_w_nameList(data.Dataset):
    '''
    can act as supervised or un-supervised based on flists
    '''
    def __init__(self, root1, root2, flist1, flist2, transform=None):

Here root1 and root2 represents the root directory for domain A and B, respectively. flist1 and flist2 contain image names for domain A and domain B. Note, if flist1 and flist2 are aligned then dataset will load paired images. To use it as unsupervised dataset loader ensure that flist1 and flist2 are not aligned.

Learning models with uncertainty

src/networks.py provides the generator and discriminator architectures.

src/utils.py provides the training API train_UGAC. The API is to train a pair of GANs, with the generators modified to predict the parameters of the generalized Gaussian distribution GGD ($\alpha$, $\beta$, $\mu$), as depicted in the above figure.

An example command to use the first API is:

#first instantiate the generators and discriminators
netG_A = CasUNet_3head(3,3)
netD_A = NLayerDiscriminator(3, n_layers=4)
netG_B = CasUNet_3head(3,3)
netD_B = NLayerDiscriminator(3, n_layers=4)

netG_A, netD_A, netG_B, netD_B = train_UGAC(
    netG_A, netG_B,
    netD_A, netD_B,
    train_loader,
    dtype=torch.cuda.FloatTensor,
    device='cuda',
    num_epochs=10,
    init_lr=1e-5,
    ckpt_path='../ckpt/ugac',
    list_of_hp = [1, 0.015, 0.01, 0.001, 1, 0.015, 0.01, 0.001, 0.05, 0.05, 0.01],
)

This will save checkpoints in ckpt/ named as ugac_eph*.pth. The arguement list_of_hp is a list of all the hyper-parameters representing weights of different weigths in the loss function.

Apart from the code in this repository, we also use the code from many other repositories like this, this, and this.

Bibtex

If you find the bits from this project helpful, please cite the following works:

Owner
EML Tübingen
Explainable Machine Learning group at University of Tübingen
EML Tübingen
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations This is the authors' implementation of Unsupervised Adversarial Learning of

Dwango Media Village 140 Dec 07, 2022
Source code for our CVPR 2019 paper - PPGNet: Learning Point-Pair Graph for Line Segment Detection

PPGNet: Learning Point-Pair Graph for Line Segment Detection PyTorch implementation of our CVPR 2019 paper: PPGNet: Learning Point-Pair Graph for Line

SVIP Lab 170 Oct 25, 2022
WebUAV-3M: A Benchmark Unveiling the Power of Million-Scale Deep UAV Tracking

WebUAV-3M: A Benchmark Unveiling the Power of Million-Scale Deep UAV Tracking [Paper Link] Abstract In this work, we contribute a new million-scale Un

25 Jan 01, 2023
[TNNLS 2021] The official code for the paper "Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement"

CSDNet-CSDGAN this is the code for the paper "Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement" Environment Preparing pyt

Jiaao Zhang 17 Nov 05, 2022
Breaking the Dilemma of Medical Image-to-image Translation

Breaking the Dilemma of Medical Image-to-image Translation Supervised Pix2Pix and unsupervised Cycle-consistency are two modes that dominate the field

Kid Liet 86 Dec 21, 2022
Official PyTorch implementation of RIO

Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection Figure 1: Our proposed Resampling at image-level and obect-

NVIDIA Research Projects 17 May 20, 2022
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR 2018).

Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR2018) By Zilong Huang, Xinggang Wang, Jiasi Wang, Wenyu Liu and J

Zilong Huang 245 Dec 13, 2022
AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Models

AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Models Description

Angel de Paula 0 Jun 08, 2022
An self sufficient AI that crawls the web to learn how to generate art from keywords

Roxx-IO - The Smart Artist AI! TO DO / IDEAS Implement Web-Scraping Functionality Figure out a less annoying (and an off button for it) text to speech

Tatz 5 Mar 21, 2022
Official repository of Semantic Image Matting

Semantic Image Matting This is the official repository of Semantic Image Matting (CVPR2021). Overview Natural image matting separates the foreground f

192 Dec 29, 2022
The codes I made while I practiced various TensorFlow examples

TensorFlow_Exercises The codes I made while I practiced various TensorFlow examples About the codes I didn't create these codes by myself, but re-crea

Terry Taewoong Um 614 Dec 08, 2022
the official implementation of the paper "Isometric Multi-Shape Matching" (CVPR 2021)

Isometric Multi-Shape Matching (IsoMuSh) Paper-CVF | Paper-arXiv | Video | Code Citation If you find our work useful in your research, please consider

Maolin Gao 9 Jul 17, 2022
PyTorch-based framework for Deep Hedging

PFHedge: Deep Hedging in PyTorch PFHedge is a PyTorch-based framework for Deep Hedging. PFHedge Documentation Neural Network Architecture for Efficien

139 Dec 30, 2022
The code of "Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer".

Code data_preprocess.py: preprocess data for Dependent-T5. parameters.py: define parameters of Dependent-T5. train_tools.py: traning and evaluation co

1 Apr 21, 2022
Fibonacci Method Gradient Descent

An implementation of the Fibonacci method for gradient descent, featuring a TKinter GUI for inputting the function / parameters to be examined and a matplotlib plot of the function and results.

Emma 1 Jan 28, 2022
GenGNN: A Generic FPGA Framework for Graph Neural Network Acceleration

GenGNN: A Generic FPGA Framework for Graph Neural Network Acceleration Stefan Abi-Karam*, Yuqi He*, Rishov Sarkar*, Lakshmi Sathidevi, Zihang Qiao, Co

Sharc-Lab 19 Dec 15, 2022
PyTorch implementation of "A Two-Stage End-to-End System for Speech-in-Noise Hearing Aid Processing"

Implementation of the Sheffield entry for the first Clarity enhancement challenge (CEC1) This repository contains the PyTorch implementation of "A Two

10 Aug 19, 2022
PyTorch implementation of UPFlow (unsupervised optical flow learning)

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning By Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun Megvii

kunming luo 87 Dec 20, 2022
Tooling for converting STAC metadata to ODC data model

手语识别 0、使用到的模型 (1). openpose,作者:CMU-Perceptual-Computing-Lab https://github.com/CMU-Perceptual-Computing-Lab/openpose (2). 图像分类classification,作者:Bubbl

Open Data Cube 65 Dec 20, 2022
An official implementation of the paper Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

Sequence Feature Alignment (SFA) By Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-jun Zha, Yonggang Wen, and Dacheng Tao This repository is an o

WangWen 79 Dec 24, 2022