Augmenting Anchors by the Detector Itself

Related tags

Computer Visionaadi
Overview

Augmenting Anchors by the Detector Itself

Introduction

It is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine anchor parameters according to objects' shape and scale in a dataset, or avoid this problem by utilizing anchor-free method. In this paper, we propose a gradient-free anchor augmentation method named AADI, which means Augmenting Anchors by the Detector Itself. AADI is not an anchor-free method, but it converts the scale and aspect ratio of anchors from a continuous space to a discrete space, which greatly alleviates the problem of anchors' designation. Furthermore, AADI does not add any parameters or hyper-parameters, which is beneficial for future research and downstream tasks. Extensive experiments on COCO dataset show that AADI has obvious advantages for both two-stage and single-stage methods, specifically, AADI achieves at least 2.1 AP improvements on Faster R-CNN and 1.6 AP improvements on RetinaNet, using ResNet-50 model. We hope that this simple and cost-efficient method can be widely used in object detection.

  • For RPN

    • Baseline

      Num anchors AR100 AR1000 ARs ARm ARl
      1 45.5 55.6 31.4 52.8 60.0
      3 45.7 58.0 31.4 52.7 61.1
    • Ablation Study

      dilation Anchor Guided AR100 AR1000 ARs ARm ARl
      1 52.8 60.6 40.2 60.8 63.6
      2 54.8 64.7 39.0 63.1 70.6
      2 56.3 66.7 39.5 64.9 73.4
      3 53.7 64.0 35.4 62.1 73.9
      3 55.6 67.6 36.1 64.3 77.6
      4 52.2 60.5 30.9 61.3 76.6
      4 54.4 65.5 33.0 63.7 78.9
  • For RetinaNet

    • Ablation Study

      AADI dilation AP AP50 AP75 APs APm APl
      1 38.2 58.4 41.1 24.3 42.2 48.5
      1 37.3 56.4 40.2 22.0 39.9 46.8
      2 39.8 57.5 43.5 22.1 43.5 50.6
      3 38.3 54.6 41.7 20.0 43.1 51.1
    • With IoU

      AP AP50 AP75 APs APm APl
      40.2 57.7 43.8 24.1 43.1 52.2
    • With 3x schedule (RetinaNet with giou, AADI with smooth l1)

      Model AP AP50 AP75 APs APm APl
      RetinaNet 39.6 59.3 42.2 24.9 43.3 50.7
      AADI-RetinaNet 41.4 59.3 45.2 24.8 44.9 54.0
  • For Faster R-CNN

    • Ablation Study

      AADI dilation AP AP50 AP75 APs APm APl FPS
      1(3 anchors) 37.9 58.8 41.1 22.4 41.1 49.1 26.3
      2 40.3 59.3 44.3 24.2 43.3 52.2 22.4
      3 40.8 59.5 45.0 24.0 44.6 53.1 22.4
      4 40.5 58.7 44.6 23.2 44.8 52.7 22.3
    • 3x schedule

      Backbone AP AP50 AP75 APs APm APl FPS
      R-50 FPN 42.5 61.2 46.5 25.3 46.2 55.5 22.6
      DCN-50 FPN 44.1 63.1 48.2 28.3 46.9 58.4 20.1
      R-101 FPN 44.5 63.2 48.7 26.9 48.3 57.4 17.4
  • Detectron2

Detectron2 is Facebook AI Research's next generation library that provides state-of-the-art detection and segmentation algorithms. It is the successor of Detectron and maskrcnn-benchmark. It supports a number of computer vision research projects and production applications in Facebook.

Installation

See installation instructions.

Getting Started

See Getting Started with Detectron2, and the Colab Notebook to learn about basic usage.

Learn more at our documentation.

Citing Detectron2

@misc{wu2019detectron2,
  author =       {Yuxin Wu and Alexander Kirillov and Francisco Massa and
                  Wan-Yen Lo and Ross Girshick},
  title =        {Detectron2},
  howpublished = {\url{https://github.com/facebookresearch/detectron2}},
  year =         {2019}
}

@misc{wan2021augmenting,
      title={Augmenting Anchors by the Detector Itself}, 
      author={Xiaopei Wan and Shengjie Chen and Yujiu Yang and Zhenhua Guo and Fangbo Tao},
      year={2021},
      eprint={2105.14086},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
Demo for the paper "Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation"

Streaming speaker diarization Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation by Juan Manuel Coria, Hervé

Juanma Coria 185 Jan 01, 2023
An interactive interface for using OpenCV's GrabCut algorithm for image segmentation.

Interactive GrabCut An interactive interface for using OpenCV's GrabCut algorithm for image segmentation. Setup Install dependencies: pip install nump

Jason Y. Zhang 16 Oct 10, 2022
Handwritten_Text_Recognition

Deep Learning framework for Line-level Handwritten Text Recognition Short presentation of our project Introduction Installation 2.a Install conda envi

24 Jul 15, 2022
PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

Description This is a PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector. Only RBOX part is implemented. Using dice loss

365 Dec 20, 2022
📷 Face Recognition using Haar-Cascade Classifier, OpenCV, and Python

Face-Recognition-System Face Recognition using Haar-Cascade Classifier, OpenCV and Python. This project is based on face detection and face recognitio

1 Jan 10, 2022
BoxToolBox is a simple python application built around the openCV library

BoxToolBox is a simple python application built around the openCV library. It is not a full featured application to guide you through the w

František Horínek 1 Nov 12, 2021
Page to PAGE Layout Analysis Tool

P2PaLA Page to PAGE Layout Analysis (P2PaLA) is a toolkit for Document Layout Analysis based on Neural Networks. 💥 Try our new DEMO for online baseli

Lorenzo Quirós Díaz 180 Nov 24, 2022
Python Computer Vision from Scratch

This repository explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both f

Milaan Parmar / Милан пармар / _米兰 帕尔马 221 Dec 26, 2022
Train custom VR face tracking parameters

Pal Buddy Guy: The anipal's best friend This is a small script to improve upon the tracking capabilities of the Vive Pro Eye and facial tracker. You c

7 Dec 12, 2021
PyNeuro is designed to connect NeuroSky's MindWave EEG device to Python and provide Callback functionality to provide data to your application in real time.

PyNeuro PyNeuro is designed to connect NeuroSky's MindWave EEG device to Python and provide Callback functionality to provide data to your application

Zach Wang 45 Dec 30, 2022
BNF Globalization Code (CVPR 2016)

Boundary Neural Fields Globalization This is the code for Boundary Neural Fields globalization method. The technical report of the method can be found

25 Apr 15, 2022
EQFace: An implementation of EQFace: A Simple Explicit Quality Network for Face Recognition

EQFace: A Simple Explicit Quality Network for Face Recognition The first face recognition network that generates explicit face quality online.

DeepCam Shenzhen 141 Dec 31, 2022

Installations for running keras-theano on GPU Upgrade pip and install opencv2 cd ~ pip install --upgrade pip pip install opencv-python Upgrade keras

Berat Kurar Barakat 14 Sep 30, 2022
This is used to convert a string to an Image with Handwritten Characters.

Text-to-Handwriting-using-python This is used to convert a string to an Image with Handwritten Characters. text_to_handwriting(string: str, save_to: s

Akashdeep Mahata 3 Aug 15, 2022
Toolbox for OCR post-correction

Ochre Ochre is a toolbox for OCR post-correction. Please note that this software is experimental and very much a work in progress! Overview of OCR pos

National Library of the Netherlands / Research 117 Nov 10, 2022
The first open-source library that detects the font of a text in a image.

Typefont Typefont is an experimental library that detects the font of a text in a image. Usage Import the main function and invoke it like in the foll

Vasile Pește 1.6k Feb 24, 2022
Python library to extract tabular data from images and scanned PDFs

Overview ExtractTable - API to extract tabular data from images and scanned PDFs The motivation is to make it easy for developers to extract tabular d

Org. Account 165 Dec 31, 2022
Code for CVPR'2022 paper ✨ "Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model"

PPE ✨ Repository for our CVPR'2022 paper: Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-

Zipeng Xu 34 Nov 28, 2022
Read Japanese manga inside browser with selectable text.

mokuro Read Japanese manga with selectable text inside a browser. See demo: https://kha-white.github.io/manga-demo mokuro_demo.mp4 Demo contains excer

Maciej Budyś 170 Dec 27, 2022
Code release for Hu et al., Learning to Segment Every Thing. in CVPR, 2018.

Learning to Segment Every Thing This repository contains the code for the following paper: R. Hu, P. Dollár, K. He, T. Darrell, R. Girshick, Learning

Ronghang Hu 417 Oct 03, 2022