Multi-Anchor Active Domain Adaptation for Semantic Segmentation (ICCV 2021 Oral)

Related tags

Deep LearningMADA
Overview

Multi-Anchor Active Domain Adaptation for Semantic Segmentation

Munan Ning*, Donghuan Lu*, Dong Wei†, Cheng Bian, Chenglang Yuan, Shuang Yu, Kai Ma, Yefeng Zheng

paper

Table of Contents

Introduction

This respository contains the MADA method as described in the ICCV 2021 Oral paper "Multi-Anchor Active Domain Adaptation for Semantic Segmentation".

Requirements

The code requires Pytorch >= 0.4.1 with python 3.6. The code is trained using a NVIDIA Tesla V100 with 32 GB memory. You can simply reduce the batch size in stage 2 to run on a smaller memory.

Usage

  1. Preparation:
  • Download the GTA5 dataset as the source domain, and the Cityscapes dataset as the target domain.
  • Download the weights and features. Move features to the MADA directory.
  1. Setup the config files.
  • Set the data paths
  • Set the pretrained model paths
  1. Training-quick
  • To run the code with our weights and anchors (anchors/cluster_centroids_full_10.pkl):
python3 train_active_stage1.py
python3 train_active_stage2.py
  • During the training, the generated files (log file) will be written in the folder 'runs/..'.
  1. Evaluation
  • Set the config file for test (configs/test_from_city_to_gta.yml):
  • Run:
python3 test.py

to see the results.

  1. Training-whole process
  • Setting the config files.
  • Stage 1:
  • 1-save_feat_source.py: get the './features/full_dataset_objective_vectors.pkl'
python3 save_feat_source.py
  • 2-cluster_anchors_source.py: cluster the './features/full_dataset_objective_vectors.pkl' to './anchors/cluster_centroids_full_10.pkl'
python3 cluster_anchors_source.py
  • 3-select_active_samples.py: select active samples with './anchors/cluster_centroids_full_10.pkl' to 'stage1_cac_list_0.05.txt'
python3 select_active_samples.py
  • 4-train_active_stage1.py: train stage1 model with anchors './anchors/cluster_centroids_full_10.pkl' and active samples 'stage1_cac_list_0.05.txt', get the 'from_gta5_to_cityscapes_on_deeplab101_best_model_stage1.pkl', which is stored in the runs/active_from_gta_to_city_stage1
python3 train_active_stage1.py
  • Stage 2:
  • 1-save_feat_target.py: get the './features/target_full_dataset_objective_vectors.pkl.pkl'
python3 save_feat_target.py
  • 2-cluster_anchors_target.py: cluster the './features/target_full_dataset_objective_vectors.pkl' to './anchors/cluster_centroids_full_target_10.pkl'
python3 cluster_anchors_target.py
  • 3-train_active_stage2.py: train stage2 model with anchors './anchors/cluster_centroids_full_target_10.pkl' and active samples 'stage1_cac_list_0.05.txt', get the 'from_gta5_to_cityscapes_on_deeplab101_best_model_stage2.pkl'
python3 train_active_stage2.py

License

MIT

The code is heavily borrowed from the CAG_UDA (https://github.com/RogerZhangzz/CAG_UDA).

If you use this code and find it usefule, please cite:

@inproceedings{ning2021multi,
  title={Multi-Anchor Active Domain Adaptation for Semantic Segmentation},
  author={Ning, Munan and Lu, Donghuan and Wei, Dong and Bian, Cheng and Yuan, Chenglang and Yu, Shuang and Ma, Kai and Zheng, Yefeng},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={9112--9122},
  year={2021}
}

Notes

The anchors are calcuated based on features captured by decoders.

In this paper, we utilize the more powerful decoder in DeeplabV3+, it may cause somewhere unfair. So we strongly recommend the ProDA which utilize origin DeeplabV2 decoder.

Owner
Munan Ning
Munan Ning
ScriptProfilerPy - Module to visualize where your python script is slow

ScriptProfiler helps you track where your code is slow It provides: Code lines t

Lucas BLP 3 Jun 02, 2022
This is a pytorch implementation for the BST model from Alibaba https://arxiv.org/pdf/1905.06874.pdf

Behavior-Sequence-Transformer-Pytorch This is a pytorch implementation for the BST model from Alibaba https://arxiv.org/pdf/1905.06874.pdf This model

Jaime Ferrando Huertas 83 Jan 05, 2023
ML-based medical imaging using Azure

Disclaimer This code is provided for research and development use only. This code is not intended for use in clinical decision-making or for any other

Microsoft Azure 68 Dec 23, 2022
A library for researching neural networks compression and acceleration methods.

A library for researching neural networks compression and acceleration methods.

Intel Labs 100 Dec 29, 2022
Avalanche RL: an End-to-End Library for Continual Reinforcement Learning

Avalanche RL: an End-to-End Library for Continual Reinforcement Learning Avalanche Website | Getting Started | Examples | Tutorial | API Doc | Paper |

ContinualAI 43 Dec 24, 2022
Pretty Tensor - Fluent Neural Networks in TensorFlow

Pretty Tensor provides a high level builder API for TensorFlow. It provides thin wrappers on Tensors so that you can easily build multi-layer neural networks.

Google 1.2k Dec 29, 2022
Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" (RSS 2022)

Intro Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" Robotics:Science and

Yunho Kim 21 Dec 07, 2022
This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

The-Emergence-of-Objectness This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

44 Oct 08, 2022
VGGFace2-HQ - A high resolution face dataset for face editing purpose

The first open source high resolution dataset for face swapping!!! A high resolution version of VGGFace2 for academic face editing purpose

Naiyuan Liu 232 Dec 29, 2022
A simple Tensorflow based library for deep and/or denoising AutoEncoder.

libsdae - deep-Autoencoder & denoising autoencoder A simple Tensorflow based library for Deep autoencoder and denoising AE. Library follows sklearn st

Rajarshee Mitra 147 Nov 18, 2022
Multiple Object Tracking with Yolov5!

Tracking with yolov5 This implementation is for who need to tracking multi-object only with detector. You can easily track mult-object with your well

9 Nov 08, 2022
A Python-based development platform for automated trading systems - from backtesting to optimisation to livetrading.

AutoTrader AutoTrader is Python-based platform intended to help in the development, optimisation and deployment of automated trading systems. From sim

Kieran Mackle 485 Jan 09, 2023
CS550 Machine Learning course project on CNN Detection.

CNN Detection (CS550 Machine Learning Project) Team Members (Tensor) : Yadava Kishore Chodipilli (11940310) Thashmitha BS (11941250) This is a work do

yaadava_kishore 2 Jan 30, 2022
TICC is a python solver for efficiently segmenting and clustering a multivariate time series

TICC TICC is a python solver for efficiently segmenting and clustering a multivariate time series. It takes as input a T-by-n data matrix, a regulariz

406 Dec 12, 2022
DeepLearning Anomalies Detection with Bluetooth Sensor Data

Final Year Project. Constructing models to create offline anomalies detection using Travel Time Data collected from Bluetooth sensors along the route.

1 Jan 10, 2022
PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-supervised ViT.

MAE for Self-supervised ViT Introduction This is an unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-sup

36 Oct 30, 2022
Riemannian Convex Potential Maps

Modeling distributions on Riemannian manifolds is a crucial component in understanding non-Euclidean data that arises, e.g., in physics and geology. The budding approaches in this space are limited b

Facebook Research 61 Nov 28, 2022
Faster RCNN with PyTorch

Faster RCNN with PyTorch Note: I re-implemented faster rcnn in this project when I started learning PyTorch. Then I use PyTorch in all of my projects.

Long Chen 1.6k Dec 23, 2022
FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

HKBU High Performance Machine Learning Lab 6 Nov 18, 2022
Fast and robust clustering of point clouds generated with a Velodyne sensor.

Depth Clustering This is a fast and robust algorithm to segment point clouds taken with Velodyne sensor into objects. It works with all available Velo

Photogrammetry & Robotics Bonn 957 Dec 21, 2022