CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images

Related tags

Deep LearningCFC-Net
Overview

CFC-Net

This project hosts the official implementation for the paper:

CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images [arxiv]

(paper and the complete code are coming soon....)

Abstract

In this paper, we discuss the role of discriminative features in object detection, and then propose a Critical Feature Capturing Network (CFC-Net) to improve detection accuracy from three aspects: building powerful feature representation, refining preset anchors, and optimizing label assignment. The proposed framework creates more powerful semantic representations for objects in remote sensing images and achieves high-performance real-time object detection. Note that our model is a one-stage detector with only one anchor on each location in feature maps, which is equivalent to the anchor-free methods, thus the inference speed is faster.

Requirements

  • torch >= 1.1
  • CUDA version >=10.0

Installation

pip install -r requirements.txt
pip install git+git://github.com/lehduong/torch-warmup-lr.git

cd $ROOT/utils
sh make.sh

cd $ROOT/datasets/DOTA_devkit
sudo apt-get install swig
swig -c++ -python polyiou.i
python setup.py build_ext --inplace

Training

  1. Move the dataset to the $ROOT directory.
  2. Generate imageset files for dataset division via:
cd $ROOT/datasets
python generate_imageset.py
  1. Modify the configuration file hyp.py and arguments in train.py, then start training:
python train.py

Inference

You can use the following command to test a dataset. Note that weight, img_dir, dataset,hyp should be modified as appropriate.

python demo.py

Evaluation

Different datasets use different test methods. For UCAS-AOD/HRSC2016/VOC/NWPU VHR-10, you need to prepare labels in the appropriate format in advance. Take evaluation on HRSC2016 for example:

cd $ROOT/datasets/evaluate
python hrsc2gt.py

then you can conduct evaluation:

python eval.py

Note that :

  • the script needs to be executed only once, but testing on different datasets needs to be executed again.
  • the imageset file used in hrsc2gt.py is generated from generate_imageset.py.

Main Results

Method Dataset Backbone Input Size mAP
CFC-Net HRSC2016 ResNet-50 416 x 416 86.3
CFC-Net HRSC2016 ResNet-101 800 x 800 89.7
CFC-Net UCAS-AOD ResNet-50 416 x 416 89.5
CFC-Net DOTA ResNet-101 800 x 800 73.5

Detections

  • Results on HRSC2016: the red bounding box and the green denotes preset anchors and detection results, respectively. HRSC_results

  • Results on DOTA:

DOTA_results

Citation

If you find our work or code useful in your research, please consider citing:

@article{ming2021cfc,
  title={CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images},
  author={Ming, Qi and Miao, Lingjuan and Zhou, Zhiqiang and Dong, Yunpeng},
  journal={arXiv preprint arXiv:2101.06849},
  year={2021}
}

If you have any questions, please contact me via issue or email.

Owner
ming71
欢迎学术交流合作[email protected]
ming71
ADSPM: Attribute-Driven Spontaneous Motion in Unpaired Image Translation

ADSPM: Attribute-Driven Spontaneous Motion in Unpaired Image Translation This repository provides a PyTorch implementation of ADSPM. Requirements Pyth

24 Jul 24, 2022
A TensorFlow implementation of SOFA, the Simulator for OFfline LeArning and evaluation.

SOFA This repository is the implementation of SOFA, the Simulator for OFfline leArning and evaluation. Keeping Dataset Biases out of the Simulation: A

22 Nov 23, 2022
UPSNet: A Unified Panoptic Segmentation Network

UPSNet: A Unified Panoptic Segmentation Network Introduction UPSNet is initially described in a CVPR 2019 oral paper. Disclaimer This repository is te

Uber Research 622 Dec 26, 2022
Edge-aware Guidance Fusion Network for RGB-Thermal Scene Parsing

EGFNet Edge-aware Guidance Fusion Network for RGB-Thermal Scene Parsing Dataset and Results Test maps: 百度网盘 提取码:zust Citation @ARTICLE{ author={Zhou,

ShaohuaDong 10 Dec 08, 2022
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning DouZero is a reinforcement learning framework for DouDizhu (斗地主), t

Kwai Inc. 3.1k Jan 04, 2023
SAGE: Sensitivity-guided Adaptive Learning Rate for Transformers

SAGE: Sensitivity-guided Adaptive Learning Rate for Transformers This repo contains our codes for the paper "No Parameters Left Behind: Sensitivity Gu

Chen Liang 23 Nov 07, 2022
Pytorch implementation of our paper LIMUSE: LIGHTWEIGHT MULTI-MODAL SPEAKER EXTRACTION.

LiMuSE Overview Pytorch implementation of our paper LIMUSE: LIGHTWEIGHT MULTI-MODAL SPEAKER EXTRACTION. LiMuSE explores group communication on a multi

Auditory Model and Cognitive Computing Lab 17 Oct 26, 2022
Reference implementation for Structured Prediction with Deep Value Networks

Deep Value Network (DVN) This code is a python reference implementation of DVNs introduced in Deep Value Networks Learn to Evaluate and Iteratively Re

Michael Gygli 55 Feb 02, 2022
Code for paper PairRE: Knowledge Graph Embeddings via Paired Relation Vectors.

PairRE Code for paper PairRE: Knowledge Graph Embeddings via Paired Relation Vectors. This implementation of PairRE for Open Graph Benchmak datasets (

Alipay 65 Dec 19, 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 01, 2022
Official git repo for the CHIRP project

CHIRP Project This is the official git repository for the CHIRP project. Pull requests are accepted here, but for the moment, the main repository is s

Dan Smith 77 Jan 08, 2023
Official PyTorch implementation of Less is More: Pay Less Attention in Vision Transformers.

Less is More: Pay Less Attention in Vision Transformers Official PyTorch implementation of Less is More: Pay Less Attention in Vision Transformers. By

73 Jan 01, 2023
Catbird is an open source paraphrase generation toolkit based on PyTorch.

Catbird is an open source paraphrase generation toolkit based on PyTorch. Quick Start Requirements and Installation The project is based on PyTorch 1.

Afonso Salgado de Sousa 5 Dec 15, 2022
PSANet: Point-wise Spatial Attention Network for Scene Parsing, ECCV2018.

PSANet: Point-wise Spatial Attention Network for Scene Parsing (in construction) by Hengshuang Zhao*, Yi Zhang*, Shu Liu, Jianping Shi, Chen Change Lo

Hengshuang Zhao 217 Oct 30, 2022
Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.

FC-DenseNet-Tensorflow This is a re-implementation of the 100 layer tiramisu, technically a fully convolutional DenseNet, in TensorFlow (Tiramisu). Th

Hasnain Raza 121 Oct 12, 2022
Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

EMS-COLS-recourse Initial Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions Folder structure: data folder contains raw an

Prateek Yadav 1 Nov 25, 2022
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

Imbalanced Dataset Sampler Introduction In many machine learning applications, we often come across datasets where some types of data may be seen more

Ming 2k Jan 08, 2023
Malware Bypass Research using Reinforcement Learning

Malware Bypass Research using Reinforcement Learning

Bobby Filar 76 Dec 26, 2022
HackBMU-5.0-Team-Ctrl-Alt-Elite - HackBMU 5.0 Team Ctrl Alt Elite

HackBMU-5.0-Team-Ctrl-Alt-Elite The search is over. We present to you ‘Health-A-

3 Feb 19, 2022
Block Sparse movement pruning

Movement Pruning: Adaptive Sparsity by Fine-Tuning Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; ho

Hugging Face 54 Dec 20, 2022