Open AccessPosted Content
You Only Look Once: Unified, Real-Time Object Detection
Reads0
Chats0
TLDR
YOLO as discussed by the authors predicts bounding boxes and class probabilities directly from full images in one evaluation, which can be optimized end-to-end directly on detection performance, and achieves state-of-the-art performance.Abstract:
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.
Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.read more
Citations
More filters
Posted Content
YOLO9000: Better, Faster, Stronger
Joseph Redmon,Ali Farhadi +1 more
TL;DR: YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories, is introduced and a method to jointly train on object detection and classification is proposed, both novel and drawn from prior work.
Journal ArticleDOI
Deep learning for visual understanding
TL;DR: The state-of-the-art in deep learning algorithms in computer vision is reviewed by highlighting the contributions and challenges from over 210 recent research papers, and the future trends and challenges in designing and training deep neural networks are summarized.
Proceedings ArticleDOI
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
TL;DR: DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance and is 5 times faster than the closest competitor - Deep-Deblur.
Posted Content
DenseCap: Fully Convolutional Localization Networks for Dense Captioning
TL;DR: A Fully Convolutional Localization Network (FCLN) architecture is proposed that processes an image with a single, efficient forward pass, requires no external regions proposals, and can be trained end-to-end with asingle round of optimization.
Journal ArticleDOI
An overview of deep learning in medical imaging focusing on MRI
Alexander Lundervold,Alexander Lundervold,Arvid Lundervold,Arvid Lundervold,Arvid Lundervold +4 more
TL;DR: This paper indicates how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction, and provides a starting point for people interested in experimenting and contributing to the field of deep learning for medical imaging.
References
More filters
Posted Content
Real-Time Grasp Detection Using Convolutional Neural Networks
Joseph Redmon,Anelia Angelova +1 more
TL;DR: In this paper, a convolutional neural network (CNN) is used for robotic grasp detection, which performs single-stage regression to graspable bounding boxes without using standard sliding window or region proposal techniques.
Proceedings ArticleDOI
The Fastest Deformable Part Model for Object Detection
TL;DR: This paper solves the speed bottleneck of deformable part model (DPM), while maintaining the accuracy in detection on challenging datasets, and achieves state-of-the-art accuracy on pedestrian and face detection task with frame-rate speed.
Proceedings Article
Region-based Segmentation and Object Detection
TL;DR: This work proposes a hierarchical region-based approach to joint object detection and image segmentation that simultaneously reasons about pixels, regions and objects in a coherent probabilistic model and gives a single unified description of the scene.
Book ChapterDOI
30Hz Object Detection with DPM V5
TL;DR: An implementation of the Deformable Parts Model that operates in a user-defined time-frame that uses a variety of mechanism to trade-off speed against accuracy, and exploits a series of important speedup mechanisms.
Posted Content
Object Detection Networks on Convolutional Feature Maps
TL;DR: It is shown by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015.