(CVPR2021) DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

Related tags

Deep Learning DANNet
Overview

DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

CVPR2021(oral) [arxiv] Framework

Requirements

  • python3.7
  • pytorch==1.5.0
  • cuda10.2

Datasets

Cityscapes: Please follow the instructions in Cityscape to download the training set.

Dark-Zurich: Please follow the instructions in Dark-Zurich to download the training/val/test set.

Testing

If needed, please directly download the visualization results of our method for Dark-zurich-val and Dark-zurich-test. Framework To reproduce the reported results in our paper (on Dark-Zurich val), please follow these steps:

Step1: download the [trained models](https://www.dropbox.com/s/fmlq806p2wqf311/trained_models.zip?dl=0) and put it in the root.
Step2: change the data and model paths in configs/test_config.py
Step3: run "python evaluation.py"
Step4: run "python compute_iou.py"

If you want to evaluate your methods on the test set, please visit this challenge for more details.

Training

If you want to train your own models, please follow these steps:

Step1: download the [pre-trained models](https://www.dropbox.com/s/3n1212kxuv82uua/pretrained_models.zip?dl=0) and put it in the root.
Step2: change the data and model paths in configs/train_config.py
Step3: run "python train.py"

Acknowledgments

The code is based on AdaptSegNet, PSPNet, Deeplab-v2 and RefineNet.

Related works

Citation

If you think this paper is useful for your research, please cite our paper:

@InProceedings{WU_2021_CVPR,
author = {Wu, Xinyi and Wu, Zhenyao and Guo, Hao and Ju, Lili and Wang, Song},
title = {DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}

Contact

Comments
  • Reproduce results on DarkZurich val set

    Reproduce results on DarkZurich val set

    Hi,

    I am trying to reproduce the reported result on DarkZurich validation set: 36.76. I used your codes and the same default training configs, and trained the model on a single Tesla V100 GPU with PyTorch 1.7.0. The validation miou is 34.86. Is this result in a reasonable variance range?

    opened by DeppMeng 7
  • Testing question

    Testing question

    During the test, the generated results need to be uploaded to the codalab website. The folders to be uploaded are confidence, labeltraining and labeltraining_ Invalid, in which the pictures in the "confidence" folder are written in your testing code. What pictures do you need to put in the "labeltraining_ids" and "labeltraining ids_invalid" folders? Can this part of the code be made public？Thank you !

    opened by WANGLEKV 4
  • training question

    training question

    Each time i trained DANNet the performance is derived differently. Such as in Dark zurich val dataset miou= 35.5 ~ 36.5. Is this because of gan's learning difficulties?

    opened by jimmy9704 3
  • Memory question

    Memory question

    Thanks for your code!

    As you said in the paper, you implement the code on a single GTX 2080TI GPU, but I encounter the out of memory error when training on a single GTX 2080TI GPU. What is the exact memory space you use?

    I encounter the ModuleNotFoundError: No module named 'joint_transforms' here. I think you could change the code to:

    from . import joint_transforms as joint_transforms
from . import joint_transforms2 as joint_transforms2
from . import transforms as extended_transforms
    opened by HeliosZhao 3
  • weight decision principle

    weight decision principle

    First of all, thank you for sharing the code of this excellent study.

    I would like to give weight by label in different task datasets. However, the logic of setting the weight of each class was not found in this paper. The supplement paper is not available at present, so there is no way to know.

    Can you tell me how you decided by calculating the weight?

    Thank you for that.

    opened by Youngsplace0913 3
  • How to load Night-time Driving set

    How to load Night-time Driving set

    Thank you for sharing the code of your excellent work.

    I have a question about your implementation.

    When you evaluate your work on Night-time Driving set, did you load the dataset using cityscapes_dataset.py?

    I'm looking forward to hearing from you!

    Thanks!

    opened by jdg900 2
  • Model weight selection

    Model weight selection

    Hello! Your paper has inspired me a lot. Thank you.
    Meanwhile, I used the code you provided for training to reproduce the results. I trained 50,000 times according to the code and got a weight file for every 1,000 times. May I ask whether the final weight used for validation and testing was obtained in the last round (i.e. 50,000 round)?
    Have you used trained intermediate weights for validation and testing, such as the .pth file from 40,000 rounds of training?

    opened by creater-zq 2
  • Time question

    Time question

    Thanks for your code implementation!

    As mentioned in the paper, 3 Models RefineNet, DeepLab, and PSPNet were trained for 35,000 epochs on a single GTX 2080TI GPU. It would be beneficial to provide a rough estimate of how much time was required for each model to train?

    opened by mradul2 1
  • enhancement = enhancement*mean_std[1]+mean_std[0]

    enhancement = enhancement*mean_std[1]+mean_std[0]

    Hello! I encountered an error while running evaluate.py

    • NameError: name 'mean_std' is not defined

    I tried to find the definition of the variable mean_std but could not find it, could you please tell me how to fix this error? thanks

    opened by creater-zq 1
Owner
W-zx-Y
W-zx-Y
GitHub
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
[CVPR2021] Domain Consensus Clustering for Universal Domain Adaptation

[CVPR2021] Domain Consensus Clustering for Universal Domain Adaptation [Paper] Prerequisites To install requirements: pip install -r requirements.txt

Guangrui Li 84 Dec 26, 2022
Adversarial Adaptation with Distillation for BERT Unsupervised Domain Adaptation

Knowledge Distillation for BERT Unsupervised Domain Adaptation Official PyTorch implementation | Paper Abstract A pre-trained language model, BERT, ha

Minho Ryu 29 Nov 30, 2022
Code for our NeurIPS 2021 paper Mining the Benefits of Two-stage and One-stage HOI Detection

CDN Code for our NeurIPS 2021 paper "Mining the Benefits of Two-stage and One-stage HOI Detection". Contributed by Aixi Zhang*, Yue Liao*, Si Liu, Mia

null 71 Dec 14, 2022
Code for Mining the Benefits of Two-stage and One-stage HOI Detection

Status: Archive (code is provided as-is, no updates expected) PPO-EWMA [Paper] This is code for training agents using PPO-EWMA and PPG-EWMA, introduce

OpenAI 33 Dec 15, 2022
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation [arxiv] This is the official repository for CDTrans: Cross-domain Transformer for

null 238 Dec 22, 2022
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

[ICCV2021] TransReID: Transformer-based Object Re-Identification [pdf] The official repository for TransReID: Transformer-based Object Re-Identificati

DamoCV 569 Dec 30, 2022
[CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

LBYL-Net This repo implements paper Look Before You Leap: Learning Landmark Features For One-Stage Visual Grounding CVPR 2021. Getting Started Prerequ

SVIP Lab 45 Dec 12, 2022
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in clustering (CVPR2021)

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering Jang Hyun Cho1, Utkarsh Mall2, Kavita Bala2, Bharath Harihar

Jang Hyun Cho 164 Dec 30, 2022
Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing, Pattern Recognition

USDAN The implementation of Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing, which is accepte

null 11 Nov 3, 2022
PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021)

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021) This repo presents PyTorch implementation of M

Evgeny 79 Dec 19, 2022
Official implementation of "DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation"

DSP Official implementation of "DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation". Accepted by ACM Multimedia 2021. Authors

null 20 Oct 24, 2022
Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition"

Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition", accepted at ACL 2021. For details of the model and experiments, please see our paper.

tricktreat 87 Dec 16, 2022
Virtual Dance Reality Stage: a feature that offers you to share a stage with another user virtually

Portrait Segmentation using Tensorflow This script removes the background from an input image. You can read more about segmentation here Setup The scr

null 291 Dec 24, 2022
code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"

SHOT++ Code for our TPAMI submission "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer" that is ext

null 75 Dec 16, 2022
The official codes of "Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners".

SSL models are Strong UDA learners Introduction This is the official code of paper "Semi-supervised Models are Strong Unsupervised Domain Adaptation L

Yabin Zhang 26 Dec 26, 2022
A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation(DANN), support Office-31 and Office-Home dataset

DANN A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation Prerequisites Linux or OSX NVIDIA GPU + CUDA (may CuDNN) and corre

null 8 Apr 16, 2022
IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020)

This repo is the official implementation of our paper "Instance Adaptive Self-training for Unsupervised Domain Adaptation". The purpose of this repo is to better communicate with you and respond to your questions. This repo is almost the same with Another-Version, and you can also refer to that version.

CVSM Group - email: czhu@bupt.edu.cn 84 Dec 12, 2022
Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

TVT Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation Datasets: Digit: MNIST, SVHN, USPS Object: Office, Office-Home, Vi

null 37 Dec 15, 2022