Open AccessProceedings Article
Faster R-CNN: towards real-time object detection with region proposal networks
Shaoqing Ren,Kaiming He,Ross Girshick,Jian Sun +3 more
- Vol. 28, pp 91-99
Reads0
Chats0
TLDR
Ren et al. as discussed by the authors proposed a region proposal network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.Abstract:
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R-CNN [5] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolutional features. For the very deep VGG-16 model [19], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2% mAP) and 2012 (70.4% mAP) using 300 proposals per image. Code is available at https://github.com/ShaoqingRen/faster_rcnn.read more
Citations
More filters
Posted Content
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
TL;DR: In this article, a region-based neural network is trained to directly infer the correspondence from observed pixels to the shared object representation (NOCS) along with other object information such as class label and instance mask.
Book ChapterDOI
3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-view Spatial Feature Fusion for 3D Object Detection
TL;DR: Li et al. as discussed by the authors proposed a 3D-CVF that combines the camera and LiDAR features using the cross-view spatial feature fusion strategy, which achieved state-of-the-art performance in the KITTI benchmark.
Proceedings ArticleDOI
Scale-Adaptive Convolutions for Scene Parsing
TL;DR: The proposed scale-adaptive convolutions are not only differentiable to learn the convolutional parameters and scale coefficients in an end-to-end way, but also of high parallelizability for the convenience of GPU implementation.
Proceedings ArticleDOI
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
TL;DR: CoupleNet as discussed by the authors proposes a fully convolutional network, named CoupleNet, to couple the global structure with local parts for object detection, where the object proposals obtained by the RPN are fed into the coupling module which consists of two branches.
Proceedings ArticleDOI
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
TL;DR: A Category Traversal Module is introduced that can be inserted as a plug-and-play module into most metric-learning based few-shot learners, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space.
References
More filters
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.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
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.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.