YOLO9000: Better, Faster, Stronger

@article{Redmon2017YOLO9000BF,
  title={YOLO9000: Better, Faster, Stronger},
  author={Joseph Redmon and Ali Farhadi},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={6517-6525}
}
  • Joseph Redmon, Ali Farhadi
  • Published 25 December 2016
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. [] Key Method The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. Using a novel, multi-scale training method the same YOLOv2 model can run at varying sizes, offering an easy tradeoff between speed and accuracy. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster…
SS-YOLO: An Object Detection Algorithm based on YOLOv3 and ShuffleNet
  • Yong Li, C. Lv
  • Computer Science
    2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)
  • 2020
TLDR
SS-YOLO builds a feature extraction network with reference to the structure of ShuffleNet, which improves accuracy while ensuring the speed, and improves the mean average precision by 6.5% and frames per second by 4 on the PASCAL VOC2007 dataset.
TF-YOLO: An Improved Incremental Network for Real-Time Object Detection
TLDR
Experimental results demonstrate that the proposed TF-YOLO method is a smaller, faster and more efficient network model increasing the performance of end-to-end training and real-time object detection for a variety of devices.
Object Detection through Modified YOLO Neural Network
TLDR
A modified YOLOv1 based neural network based on an inception model with a convolution kernel of 1   1 is added, which reduced the number of weight parameters of the layers and the proposed method achieved better performance.
YOLO v3-Tiny: Object Detection and Recognition using one stage improved model
TLDR
This paper presents the fundamental overview of object detection methods by including two classes of object detectors, including YOLO v1, v2, v3, and SSD, and its comparison with previous methods for detection and recognition of object is described graphically.
An object detection system based on YOLO in traffic scene
TLDR
A new object detection method, OYOLO (Optimized YOLO), is produced, which is 1.18 times faster than YolO, while outperforming other region-based approaches like R-CNN in accuracy.
Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
TLDR
The evolutionary deep intelligence framework is leveraged to evolve the YOLOv2 network architecture and produce an optimized architecture that has 2.8X fewer parameters with just a ~2% IOU drop, and a motion-adaptive inference method is introduced into the proposed Fast Y OLO framework to reduce the frequency of deep inference with O-YOLO v2 based on temporal motion characteristics.
An Object Detection Algorithm Based on Improved Network Structure
  • Haohao Du, Shasha Li, Yongjun Li
  • Computer Science
    2019 6th International Conference on Information Science and Control Engineering (ICISCE)
  • 2019
TLDR
This work changed the original feature extraction network to extract feature images by using depth separable convolutions and convolution kernels of different sizes and upgraded the loss function of Yolov3 to improve the detection speed.
An Object Detection Algorithm Based on Improved Network Structure
TLDR
This work changed the original feature extraction network to extract feature images by using depth separable convolutions and convolution kernels of different sizes and upgraded the loss function of Yolov3 to improve the detection speed.
Tinier-YOLO: A Real-Time Object Detection Method for Constrained Environments
TLDR
Tinier-YOLO is proposed to further shrink the model size while achieving improved detection accuracy and real-time performance and it posses comparable results in mAP and faster runtime speed with smaller model size and BFLOP/s value compared with other lightweight models like SqueezeNet SSD and MobileNet SSD.
Multi-Thread Approach to Object Detection Using YOLOv3
  • Rayan Abri, Sara Abri, Anıl Yarıcı, Salih Çetin
  • Computer Science
    2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR)
  • 2020
TLDR
This paper designs a Multi-thread approach that uses YOLOv3 to perform real-time object detection with decreasing detection time per frame and aims to decrease the idle times between CPU and GPU.
...
...

References

SHOWING 1-10 OF 26 REFERENCES
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Fast R-CNN
  • Ross B. Girshick
  • Computer Science, Environmental Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
TLDR
Clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly is given and several new streamlined architectures for both residual and non-residual Inception Networks are presented.
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
TLDR
The Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest, provides strong evidence that context and multi-scale representations improve small object detection.
ImageNet Large Scale Visual Recognition Challenge
TLDR
The creation of this benchmark dataset and the advances in object recognition that have been possible as a result are described, and the state-of-the-art computer vision accuracy with human accuracy is compared.
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
TLDR
Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
...
...