Proceedings ArticleDOI
Mask R-CNN
Kaiming He,Georgia Gkioxari,Piotr Dollár,Ross Girshick +3 more
- Vol. 35, Iss: 18, pp 2980-2988
Reads0
Chats0
TLDR
This work presents a conceptually simple, flexible, and general framework for object instance segmentation, which extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.Abstract:
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without tricks, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code will be made available.read more
Citations
More filters
Proceedings ArticleDOI
Through Fog High-Resolution Imaging Using Millimeter Wave Radar
TL;DR: This paper demonstrates high-resolution imaging using millimeter Wave (mmWave) radars that can function even in dense fog and introduces HawkEye, a system that leverages a cGAN architecture to recover high-frequency shapes from raw low-resolution mmWave heat-maps.
Journal ArticleDOI
VehicleNet: Learning Robust Visual Representation for Vehicle Re-Identification
TL;DR: This paper combines the provided training set with other public vehicle datasets, i.e., VeRi-776, CompCar and VehicleID as VehicleNet, and deploys the two-stage learning strategy to minor the gap between VehicleNet and the original training set.
Journal ArticleDOI
Text Recognition in the Wild: A Survey
TL;DR: A recent literature review as discussed by the authors summarizes the fundamental problems and the state-of-the-art associated with scene text recognition, introduces new insights and ideas, provides a comprehensive review of publicly available resources, and points out directions for future work.
Journal ArticleDOI
How Do Drivers Allocate Their Potential Attention? Driving Fixation Prediction via Convolutional Neural Networks
TL;DR: The experimental results indicate that the proposed CDNN outperforms the state-of-the-art saliency models and predicts drivers’ attentional locations more accurately, and shows excellent detection of secondary important information or regions that cannot be ignored during driving if they exist.
Book ChapterDOI
Improving RetinaNet for CT lesion detection with dense masks from weak RECIST labels
Martin Zlocha,Qi Dou,Ben Glocker +2 more
TL;DR: In this article, the anchor configurations were optimized using a differential evolution search algorithm, which achieved a sensitivity of 90.77% at 4 false positives per image, significantly outperforming the best reported methods by over 5%.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: 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 understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Posted Content
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: Faster R-CNN as discussed by the authors proposes a Region Proposal Network (RPN) to generate high-quality region proposals, which are used by Fast R-NN for detection.