CSAC - Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization

Related tags

Deep Learning CSAC
Overview

CSAC

Introduction

This repository contains the implementation code for paper:

Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization

Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, Lanfen Lin

arXiv preprint, 2021

[arXiv]

Brief Abstract for the Paper


The existing domain generalization (DG) methods usually exploit the fusion of shared multi-source data for capturing domain invariance and training a generalizable model, which raises a dilemma between the generalization learning with shared multi-source data and the privacy protection of real-world sensitive data.

We introduce a separated domain generalization task with separated source datasets that can only be accessed locally for data privacy protection.

We propose a novel solution called Collaborative Semantic Aggregation and Calibration (CSAC) to enable this challenging task via local semantic acquisition, data-free semantic aggregation, and cross-layer semantic calibration.

Requirements

You may need to build suitable Python environment by installing the following packages (Anaconda is recommended).

  • python 3.8
  • pytorch 1.8.1 (with cuda 11.3)
  • torchvision 0.9.1
  • tensorboardx 2.4
  • numpy 1.21
  • qpsolvers 1.7

Device:

  • GPU with VRAM > 11GB (strictly).
  • Memory > 8GB.

Data Preparation

We list the adopted datasets in the following.

Datasets Download link
PACS [1] https://dali-dl.github.io/project_iccv2017.html
VLCS [2] http://www.mediafire.com/file/7yv132lgn1v267r/vlcs.tar.gz/file

Please note:

  • Our dataset split follows previous works like RSC (Code) [3].
  • Although these datasets are open-sourced, you may need to have permission to use the datasets under the datasets' license.
  • If you're a dataset owner and do not want your dataset to be included here, please get in touch with us via a GitHub issue. Thanks!

Usage

  1. Prepare the datasets.
  2. Update root_dir in configs/datasets/dg/pacs.yaml/ and configs/datasets/dg/vlcs.yaml/ with the paths of PACS and VLCS datasets, respectively.
  3. Run the code with command:
nohup sh run.sh > run.txt 2>&1 &
  1. Check results in logs/(dataset)_(network)/(target domain)/(time)/logs.txt .

Citation

If you find our code or idea useful for your research, please consider citing our work.

@article{yuan2021collaborative,
  title={Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization},
  author={Yuan, Junkun and Ma, Xu and Chen, Defang and Kuang, Kun and Wu, Fei and Lin, Lanfen},
  journal={arXiv e-prints},
  pages={arXiv--2110},
  year={2021}
}

Contact

If you have any questions, feel free to contact us through email ([email protected] or [email protected]) or GitHub issues. Thanks!

References

[1] Li, Da, et al. "Deeper, broader and artier domain generalization." Proceedings of the IEEE international conference on computer vision. 2017.

[2] Fang, Chen, Ye Xu, and Daniel N. Rockmore. "Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias." Proceedings of the IEEE International Conference on Computer Vision. 2013.

[3] Huang, Zeyi, et al. "Self-challenging improves cross-domain generalization." Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16. Springer International Publishing, 2020.

You might also like...
This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization This codebase is the official implementation of Test-Time Classifier A

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

S2-BNN (Self-supervised Binary Neural Networks Using Distillation Loss) This is the official pytorch implementation of our paper: "S2-BNN: Bridging th

Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems
Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

ACSC Automatic extrinsic calibration for non-repetitive scanning solid-state LiDAR and camera systems. System Architecture 1. Dependency Tested with U

A python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization
A python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

Website, Tutorials, and Docs    Uncertainty Toolbox A python toolbox for predictive uncertainty quantification, calibration, metrics, and visualizatio

Aiming at the common training datsets split, spectrum preprocessing, wavelength select and calibration models algorithm involved in the spectral analysis process
Aiming at the common training datsets split, spectrum preprocessing, wavelength select and calibration models algorithm involved in the spectral analysis process

Aiming at the common training datsets split, spectrum preprocessing, wavelength select and calibration models algorithm involved in the spectral analysis process, a complete algorithm library is established, which is named opensa (openspectrum analysis).

The comma.ai Calibration Challenge!

Welcome to the comma.ai Calibration Challenge! Your goal is to predict the direction of travel (in camera frame) from provided dashcam video. This rep

The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

Representative Batch Normalization (RBN) with Feature Calibration The official implementation of the CVPR2021 oral paper: Representative Batch Normali

Improving Calibration for Long-Tailed Recognition (CVPR2021)
Improving Calibration for Long-Tailed Recognition (CVPR2021)

MiSLAS Improving Calibration for Long-Tailed Recognition Authors: Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia [arXiv] [slide] [BibTeX] Introductio

Improving Calibration for Long-Tailed Recognition (CVPR2021)
Improving Calibration for Long-Tailed Recognition (CVPR2021)

Improving Calibration for Long-Tailed Recognition (CVPR2021)

Owner
ScottYuan
CS PhD student.
ScottYuan
Implementation for "Domain-Specific Bias Filtering for Single Labeled Domain Generalization"

DSBF Introduction This repository contains the implementation code for paper: Domain-Specific Bias Filtering for Single Labeled Domain Generalization

ScottYuan 7 Jan 5, 2023
SSL_SLAM2: Lightweight 3-D Localization and Mapping for Solid-State LiDAR (mapping and localization separated) ICRA 2021

SSL_SLAM2 Lightweight 3-D Localization and Mapping for Solid-State LiDAR (Intel Realsense L515 as an example) This repo is an extension work of SSL_SL

Wang Han 王晗 1.3k Jan 8, 2023
This repo includes our code for evaluating and improving transferability in domain generalization (NeurIPS 2021)

Transferability for domain generalization This repo is for evaluating and improving transferability in domain generalization (NeurIPS 2021), based on

gordon 9 Nov 29, 2022
[CVPR'21] FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space

FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space by Quande Liu, Cheng Chen, Ji

Quande Liu 178 Jan 6, 2023
The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NIPS 2020.

Domain Generalization for Medical Imaging Classification with Linear Dependency Regularization The code release of paper 'Domain Generalization for Me

Yufei Wang 56 Dec 28, 2022
Domain Generalization with MixStyle, ICLR'21.

MixStyle This repo contains the code of our ICLR'21 paper, "Domain Generalization with MixStyle". The OpenReview link is https://openreview.net/forum?

Kaiyang 208 Dec 28, 2022
Benchmarks for semi-supervised domain generalization.

Semi-Supervised Domain Generalization This code is the official implementation of the following paper: Semi-Supervised Domain Generalization with Stoc

Kaiyang 49 Dec 10, 2022
Official implementation of paper Gradient Matching for Domain Generalization

Gradient Matching for Domain Generalisation This is the official PyTorch implementation of Gradient Matching for Domain Generalisation. In our paper,

null 94 Dec 23, 2022
The official repository for paper ''Domain Generalization for Vision-based Driving Trajectory Generation'' submitted to ICRA 2022

DG-TrajGen The official repository for paper ''Domain Generalization for Vision-based Driving Trajectory Generation'' submitted to ICRA 2022. Our Meth

Wang 25 Sep 26, 2022