Joseph Redmon, Ali Farhadi
2016 · arXiv
We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. 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 RCNN with ResNet and SSD while still running significantly faster. Finally we propose a method to jointly train on object detection and classification. Using this method we train YOLO9000 simultaneously on the COCO detection dataset and the ImageNet classification dataset. Our joint training allows YOLO9000 to predict detections for object classes that don't have labelled detection data. We validate our approach on the ImageNet detection task. YOLO9000 gets 19.7 mAP on the ImageNet detection validation set despite only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. But YOLO can detect more than just 200 classes; it predicts detections for more than 9000 different object categories. And it still runs in real-time.
Metadata: arXiv. Abstracts retain their original authors’ rights.
Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels
6 selected excerpts · 6 total mentions
For others like me who were as amused by the name, YOLO9000, it's a real thing, "a state-of-the-art, real-time object detection system that can detect over 9000 object categories". YOLO9000: Better, Faster, Stronger - https://arxiv.org/abs/1612.08242 (2016)
The original YOLO is faster (especially the "Fast YOLO" variant), but is a lot less accurate in its detections: Fast YOLO has 52.7 mean Average Precision @155 FPS vs SSD-300 with 74.3 mAP @59 FPS. But the new YOLO9000[1] architecture seems to be even better than SSD! Would like to try it at some point for sure. [1] YOLO9000: Better, Faster, Stronger: https://arxiv.org/abs/1612.08242
This is not "modern" though, the paper is quite old. He has improved it significantly since then: https://arxiv.org/abs/1612.08242. Best paper honorable mention at CVPR2017.
* Densely Connected Convolutional Networks [0] by Gao Huang, Zhuang Liu, Laurens van der Maaten, & Kilian Q. Weinberger. * Learning from Simulated and Unsupervised Images through Adversarial Training [1] by Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Joshua Susskind, Wenda Wang, & Russell Webb CVPR 2017 Best Paper Honorable Mention Awards * Annotating Object Instances with a Polygon-RNN [2] by Lluís Castrejón, Kaustav Kundu, Raquel Urtasun, & Sanja Fidler * YOLO9000: Better, Faster, Stronger [3] by Joseph Redmon & Ali Farhadi CVPR 2017 Best Student Paper Award * Computational Imaging on the Electric Grid [4] by Mark Sheinin, Yoav Y. Schechner, & Kiriakos N.…
Kutulakos CVPR 2017 Longuet-Higgins Prize (for cvpr 2007 papers that stood the test of time) * Object Retrieval with Large Vocabularies and Fast Spatial Matching [5] by James Philbin, Ondrej Chum, Michael Isard, Josef Sivic & Andrew Zisserman CVPR 2017 PAMI Young Researcher Award * Ross Girshick & Julien Mairal [0] https://arxiv.org/abs/1608.06993 [1] https://arxiv.org/abs/1612.07828 [2] https://arxiv.org/abs/1704.05548 [3] https://arxiv.org/abs/1612.08242 [4] http://openaccess.thecvf.com/content_cvpr_2017/papers/Sheini... [5] http://ieeexplore.ieee.org/document/4270197/
Their repository is pretty neat! It includes three state-of-the-art architectures in object detection: Faster-RCNN, RFCN, and SSD. It is missing YOLO [1][2], though, which shares some similarities with SSD. Another detector is the recently released Mask-RCNN [3], which of course wouldn't be possible to be included in this publication as we can't travel through time yet. [1]: https://arxiv.org/abs/1506.02640 [2]: https://arxiv.org/abs/1612.08242 [3]: https://arxiv.org/abs/1703.06870
There are quite a few papers that discuss the application R-CNN (Region-based Convolutional Neural Network) for object detection and classification [1-3]. On websites such as Medium, you can find lots of blog posts on object detection using popular frameworks such as Tensorflow (e.g. https://towardsdatascience.com/how-to-train-your-own-object-...). [1] Faster R-CNN: https://arxiv.org/abs/1506.01497 [2] Single Shot Multibox: https://arxiv.org/abs/1512.02325 [3] YOLO9000: https://arxiv.org/abs/1612.08242
More from the same topics.
Chiyuan Zhang, Samy Bengio, Moritz Hardt +2
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski +10
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands.
Ashish Vaswani, Noam Shazeer, Niki Parmar +5
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
Robert Geirhos, Patricia Rubisch, Claudio Michaelis +3
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.