Official code of "Improving Localization in Oriented Aerial Detection with Attention-Points Network"

Overview

Improving Localization in Oriented Aerial Detection with Attention-Points Network

Abstract

Localization in computer vision is the process of finding and identifying objects in an image. In aerial images, objects are usually very-small and arbitrary-oriented. Current state-of-the-art oriented aerial detectors are focused only on finding objects and fewer efforts have been made on advancing both classification (identify) and regression (find) methods. To tackle both the classification and regression problems, we used the architectures of existing oriented aerial detectors and improved their performance by inserting our designed Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses a coarse-level segmentation mask as ground-truth to learn the rich attention features essential to improve the classification of small objects. Meanwhile, BPLoss complements the existing regression loss by predicting box points and determining if they are inside or outside the oriented bounding box.

Install

Please refer to install.md for installation.

Get Started

For dataset preparation and training/testing of our model, please refer to get-started.md.

Citation

@article{Doloriel2022,
	title="Improving Localization in Oriented Aerial Detection with Attention-Points Network",
	author="Doloriel, C.T. and Cajote, R.D.",
	year="2022"
}

Acknowledgements

Below are some great resources we used. We would like to thank the owners of:

MMDetection
OBBdetection
BBoxToolKit
DOTA Dataset

You might also like...

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

Official code for

E2FGVI (CVPR 2022) This repository contains the official implementation of the following paper: Towards An End-to-End Framework for Flow-Guided Video

Jan 5, 2023

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

📖 Depth-Aware Generative Adversarial Network for Talking Head Video Generation (CVPR 2022) 🔥 If DaGAN is helpful in your photos/projects, please hel

Jan 1, 2023

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Official code for our CVPR '22 paper

Dataset Distillation by Matching Training Trajectories Project Page | Paper This repo contains code for training expert trajectories and distilling sy

Dec 23, 2022

The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.

The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.

LM-Debugger is an open-source interactive tool for inspection and intervention in transformer-based language models. This repository includes the code

Dec 28, 2022

Official code for "Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization (CVPR 2022)"

Official code for

Bridging the Gap for WSOL (CVPR 2022) This is code for "Bridging the Gap between Classification and Localization for Weakly Supervised Object Localiza

Dec 22, 2022

[MICCAI 2022] The official code for "mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation"

[MICCAI 2022] The official code for

mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation This is the implementation for the paper: mmFo

Dec 15, 2022

Official PyTorch code for Singularity in the paper "Revealing Single Frame Bias for Video-and-Language Learning"

Official PyTorch code for Singularity in the paper

Singularity Revealing Single Frame Bias for Video-and-Language Learning, arXiv 2022 Jie Lei, Tamara L. Berg, Mohit Bansal Official PyTorch code for Si

Jan 3, 2023

Official Code for Visualizing and Understanding Self-Supervised Vision Learning

PyTorch code for Visualizing and Understanding Self-Supervised Vision Learning | arXiv Gradio Web-Demo Note: Due to the latency from Hugging Face Spac

Jul 20, 2022

[IEEE TNNLS 2022] An official source code for paper Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning.

[IEEE TNNLS 2022] An official source code for paper Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning.

Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning An official source code for paper Interpolation-based Contrastive Lear

Nov 29, 2022
Owner
Chandler Timm Doloriel
Dare mighty things
Chandler Timm Doloriel
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning.

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning This is the official code for the paper CodeRL: Mastering

Salesforce 227 Dec 27, 2022
A Quick Response Code or a QR Code is a two-dimensional bar code used for its fast readability and comparatively large storage capacity.

QR-code-with-Python #A Quick Response Code or a QR Code is a two-dimensional bar code used for its fast readability and comparatively large storage ca

khushi thaker 1 Jul 20, 2022
A python package that provides Nigerian bank details(bank code, cbn code, name & ussd code)

?? nigeria_banks Nigeria Banks is a basic python package that returns details of particular bank in Nigeria. Installation You can install nigeria_bank

Devjoseph 4 Aug 6, 2022
My official submission for IET Hack'n'code 5.0. Hackathon track chosen: Sustainability and Climate Change. Webapp for Garbage Classification and Segregation

Project garbAIge Project garbAIge aims at reducing human contact to ever growing waste both unhygienic and toxic in nature and helping the planet take

Arya Shah 11 Nov 14, 2022
Official source code of Fast Point Transformer, CVPR 2022

Fast Point Transformer Project Page | Paper This repository contains the official source code and data for our paper: Fast Point Transformer Chunghyun

null 182 Dec 23, 2022
Official code for "Learning Neural Acoustic Fields"

Learning Neural Acoustic Fields Code release for: Learning Neural Acoustic Fields Paper link, Project site, For help contact afluo [a.t] andrew.cmu.ed

Andrew Luo 67 Dec 17, 2022
Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)

OpenDet Expanding Low-Density Latent Regions for Open-Set Object Detection (CVPR2022) Jiaming Han, Yuqiang Ren, Jian Ding, Xingjia Pan, Ke Yan, Gui-So

csuhan 63 Dec 23, 2022
[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

OW-DETR: Open-world Detection Transformer (CVPR 2022) [Paper] Akshita Gupta*, Sanath Narayan*, K J Joseph, Salman Khan, Fahad Shahbaz Khan, Mubarak Sh

Akshita Gupta 129 Jan 4, 2023
Official code for ROCA: Robust CAD Model Retrieval and Alignment from a Single Image (CVPR 2022)

ROCA: Robust CAD Model Alignment and Retrieval from a Single Image (CVPR 2022) Code release of our paper ROCA. Check out our video, paper, and website

null 124 Dec 30, 2022
This repo presents you the official code of "VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention"

VISTA VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention Shengheng Deng, Zhihao Liang, Lin Sun and Kui Jia* (*) Corresponding a

null 103 Dec 19, 2022