Open AccessPosted Content
You Only Look Once: Unified, Real-Time Object Detection
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
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TL;DR: This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks.
Proceedings ArticleDOI
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
Spyros Gidaris,Nikos Komodakis +1 more
TL;DR: An object detection system that relies on a multi-region deep convolutional neural network that also encodes semantic segmentation-aware features that aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization.
Book ChapterDOI
Diagnosing error in object detectors
TL;DR: This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives, and shows that sensitivity to size, localization error, and confusion with similar objects are the most impactful forms of error.
Proceedings ArticleDOI
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
TL;DR: Locality-sensitive hashing as discussed by the authors replaces the dot-product kernel operator in the convolution with a fixed number of hash-table probes that effectively sample all the filter responses in time independent of the size of the filter bank.
Book ChapterDOI
Learning to Localize Objects with Structured Output Regression
TL;DR: This work proposes to treat object localization in a principled way by posing it as a problem of predicting structured data: it model the problem not as binary classification, but as the prediction of the bounding box of objects located in images.