DIRL: Domain-Invariant Representation Learning

Related tags

Deep Learning semi-supervised-learning transfer-learning representation-learning adversarial-learning domain-adaptation robot-decluttering
Overview

DIRL: Domain-Invariant Representation Learning

Domain-Invariant Representation Learning (DIRL) is a novel algorithm that semantically aligns both the marginal and the conditional distributions across source and target enviroments. For more details, please visit: https://www.sites.google.com/view/dirl

            

dann_conceptual       [Source Only]      [Marginal Alignment Cross-Label Mismatch]      [Marginal Alignment Label Shift]      [DIRL]

Getting Started

Follow the instructions to get started after cloning the repository (tested with python3):

virtualenv --python=/usr/bin/python3 env_dirl
source env_dirl/bin/activate

pip install -r requirements.txt
python setup.py develop

Examples

Below we provide a couple of examples to illustrate the efficiency of the DIRL algorithm in learning invariant feature representations with unseen out of training distribution target environments. Customize your results by adjusting the settings and hyperparameters in the respective config files in the configs folder.

2D Synthetic Domain

CUDA_VISIBLE_DEVICES=0 python src/train_synthetic_2d.py -mode dirl -num_target_labels 4

Results are saved in the results folder with respective .yml config, results/figs and results/animations folder.

Vary the number of target examples num_target_examples and -mode among [source_only, dann, triplet, dirl] to analyse the performance of the algorithm.

Digits Bechmarks

First, download the digits datasets (required only once) in the resources folder by executing the script: python src/download_digits_datasets.py

CUDA_VISIBLE_DEVICES=1 python src/train_digits.py -mode dirl -source mnist -target mnistm -num_target_labels 10 -save_results True

Results are saved in results folder with the respective .yml config.

Vary the -source and -target options among [mnist, mnistm, svhn, usps].

-mode and -num_target_labels can be changed similarly as above.

Cite DIRL

@inproceedings{Tanwani_DIRL_CORL_20,
    title={Domain Invariant Representation Learning for Sim-to-Real Transfer},
    author={Ajay Kumar Tanwani},
    booktitle={Proceedings of the 4th Conference on Robot Learning},
    year={2020}
}
You might also like...
Implementation of CVPR 2021 paper
Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer"

SCGAN Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer" Prepare The pre-trained model is avaiable at http

null 118 Dec 12, 2022
A PyTorch Implementation of Single Shot Scale-invariant Face Detector.
A PyTorch Implementation of Single Shot Scale-invariant Face Detector.

S³FD: Single Shot Scale-invariant Face Detector A PyTorch Implementation of Single Shot Scale-invariant Face Detector. Eval python wider_eval_pytorch.

carwin 235 Jan 7, 2023
PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features Overview This repository is the Pytorch implementation of PRIN/SPRIN: On Extracting P

Yang You 17 Mar 2, 2022
An SE(3)-invariant autoencoder for generating the periodic structure of materials
An SE(3)-invariant autoencoder for generating the periodic structure of materials

Crystal Diffusion Variational AutoEncoder This software implementes Crystal Diffusion Variational AutoEncoder (CDVAE), which generates the periodic st

Tian Xie 94 Dec 10, 2022
DIR-GNN - Discovering Invariant Rationales for Graph Neural Networks
DIR-GNN - Discovering Invariant Rationales for Graph Neural Networks

DIR-GNN "Discovering Invariant Rationales for Graph Neural Networks" (ICLR 2022)

Ying-Xin (Shirley) Wu 70 Nov 13, 2022
The code for our paper submitted to RAL/IROS 2022: OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition.
The code for our paper submitted to RAL/IROS 2022: OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition.

OverlapTransformer The code for our paper submitted to RAL/IROS 2022: OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for

HAOMO.AI 136 Jan 3, 2023
Eff video representation - Efficient video representation through neural fields

Neural Residual Flow Fields for Efficient Video Representations 1. Download MPI

null 41 Jan 6, 2023
Implementation of
Implementation of "JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting"

JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting Pytorch implementation for the paper "JOKR: Joint Keypoint Repres

null 45 Dec 25, 2022
Code for CVPR2021 "Visualizing Adapted Knowledge in Domain Transfer". Visualization for domain adaptation. #explainable-ai

Visualizing Adapted Knowledge in Domain Transfer @inproceedings{hou2021visualizing, title={Visualizing Adapted Knowledge in Domain Transfer}, auth

Yunzhong Hou 80 Dec 25, 2022
Comments
  • Digits Dataset zip file problems

    Digits Dataset zip file problems

    Hello,

    I am unable to download the digits dataset zip file from the dropbox link. If I try manually as well, it downloads and then complains about unsupported format. Might be corrupted file. Can another working link be provided?

    Thanks.

    opened by aniket-9 4
  • Tensorflow version error

    Tensorflow version error

    When I run requirements.py I am getting the error ERROR: Could not find a version that satisfies the requirement tensorflow==1.11.0 (from versions: 1.13.0rc1, 1.13.0rc2, 1.13.1, 1.13.2, 1.14.0rc0, 1.14.0rc1, 1.14.0, 1.15.0rc0, 1.15.0rc1, 1.15.0rc2, 1.15.0rc3, 1.15.0, 1.15.2, 1.15.3, 1.15.4, 1.15.5, 2.0.0a0, 2.0.0b0, 2.0.0b1, 2.0.0rc0, 2.0.0rc1, 2.0.0rc2, 2.0.0, 2.0.1, 2.0.2, 2.0.3, 2.0.4, 2.1.0rc0, 2.1.0rc1, 2.1.0rc2, 2.1.0, 2.1.1, 2.1.2, 2.1.3, 2.2.0rc0, 2.2.0rc1, 2.2.0rc2, 2.2.0rc3, 2.2.0rc4, 2.2.0, 2.2.1, 2.2.2, 2.3.0rc0, 2.3.0rc1, 2.3.0rc2, 2.3.0, 2.3.1, 2.3.2, 2.4.0rc0, 2.4.0rc1, 2.4.0rc2, 2.4.0rc3, 2.4.0rc4, 2.4.0, 2.4.1, 2.5.0rc0, 2.5.0rc1) ERROR: No matching distribution found for tensorflow==1.11.0

    I am using pip 21.0.1, python 3.7.6; do I need to use an older version to get tf 1.11.0? If so, which one?

    opened by aniket-9 1
  • Full paper algorithms not included in repo. Cannot reproduce results.

    Full paper algorithms not included in repo. Cannot reproduce results.

    Hello,

    I will remove the issue if it is addressed proper.

    In this repo, why is there no way to reproduce several results from http://ajaytanwani.com/docs/Tanwani_DIRL_CORL_CR_2020.pdf using the code provided? If this not intent of providing a code base for a published paper? Why have the discussed DIRL algorithms from the paper not been included in the code?

    From my own experiments with this code, I do not align with the shared results. Please explain.

    opened by jung-lee-tech-grad 2
Owner
Ajay Tanwani
Ajay Tanwani
GitHub
This is an implementation for the CVPR2020 paper "Learning Invariant Representation for Unsupervised Image Restoration"

Learning Invariant Representation for Unsupervised Image Restoration (CVPR 2020) Introduction This is an implementation for the paper "Learning Invari

GarField 88 Nov 7, 2022
Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Learning Domain Invariant Representations in Goal-conditioned Block MDPs Beining Han, Chongyi Zheng, Harris Chan, Keiran Paster, Michael R. Zhang, Jim

Chongyi Zheng 3 Apr 12, 2022
Code for NeurIPS 2021 paper: Invariant Causal Imitation Learning for Generalizable Policies

Invariant Causal Imitation Learning for Generalizable Policies Ioana Bica, Daniel Jarrett, Mihaela van der Schaar Neural Information Processing System

Ioana Bica 17 Dec 1, 2022
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting (ICCV, 2021)

DKPNet ICCV 2021 Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting Baseline of DKPNet is availa

null 19 Oct 14, 2022
The Python ensemble sampling toolkit for affine-invariant MCMC

emcee The Python ensemble sampling toolkit for affine-invariant MCMC emcee is a stable, well tested Python implementation of the affine-invariant ense

Dan Foreman-Mackey 1.3k Dec 31, 2022
《Truly shift-invariant convolutional neural networks》(2021)

Truly shift-invariant convolutional neural networks [Paper] Authors: Anadi Chaman and Ivan Dokmanić Convolutional neural networks were always assumed

Anadi Chaman 46 Dec 19, 2022
Expressive Power of Invariant and Equivaraint Graph Neural Networks (ICLR 2021)

Expressive Power of Invariant and Equivaraint Graph Neural Networks In this repository, we show how to use powerful GNN (2-FGNN) to solve a graph alig

Marc Lelarge 36 Dec 12, 2022
Systematic generalisation with group invariant predictions

Requirements are Python 3, TensorFlow v1.14, Numpy, Scipy, Scikit-Learn, Matplotlib, Pillow, Scikit-Image, h5py, tqdm. Experiments were run on V100 GPUs (16 and 32GB).

Faruk Ahmed 30 Dec 1, 2022
PERIN is Permutation-Invariant Semantic Parser developed for MRP 2020

PERIN: Permutation-invariant Semantic Parsing David Samuel & Milan Straka Charles University Faculty of Mathematics and Physics Institute of Formal an

ÚFAL 40 Jan 4, 2023
Implementation of Invariant Point Attention, used for coordinate refinement in the structure module of Alphafold2, as a standalone Pytorch module

Invariant Point Attention - Pytorch Implementation of Invariant Point Attention as a standalone module, which was used in the structure module of Alph

Phil Wang 113 Jan 5, 2023