Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
By Shaoqing Ren, Kaiming He, Ross B. Girshick, Jian‐Yuan Sun. 2015
74,177 citations recorded by the source corpus.
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN 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. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, 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, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Andrew Zisserman
- Yi Yang
Citations in the corpus
- Deep Residual Learning for Image Recognition (2015, methodology): “The above results are only based on the proposal network (RPN) in Faster R-CNN [32].”
- Object Detection Networks on Convolutional Feature Maps (2015, methodology): “121 In Faster R-CNN [14], the shared features are also 122 used for proposing regions and reducing the heavy 123 proposal burdens.”
- End-to-End Object Detection with Transformers (2020, methodology): “Similarly to the extension of Faster R-CNN [37] to Mask R-CNN [14], DETR can be naturally extended by adding a mask head on top of the decoder outputs.”
- Momentum Contrast for Unsupervised Visual Representation Learning (2019, methodology): “The detector is Faster R-CNN [52] with a backbone of R50-dilated-C5 or R50-C4 [32] (details in appendix), with BN tuned, implemented in [60].”
- Do Better ImageNet Models Transfer Better? (2018, methodology): “In object detection, ImageNet-pretrained networks are used as backbone models for Faster R-CNN and R-FCN detection systems [57, 14].”
- What makes ImageNet good for transfer learning? (2016, methodology): “For PASCAL-DET, we used the PASCAL VOC 2007 train/val for finetuning using the experimental setup and code provided by FasterRCNN [36] and report performance on the test set.”
- Mixed Precision Training (2017, methodology): “We trained two popular detection approaches: Faster-RCNN (Ren et al., 2015) and Multibox-SSD (Liu et al., 2015a As can be seen in table 2, SSD detector failed to train in FP16 without loss-scaling.”
- Exploring Self-Attention for Image Recognition (2020, background): “These serve as the basis for models developed for other computer vision tasks, such as semantic segmentation [22, 3, 42, 44] and object detection [10, 9, 28, 21].”
- VisualBERT: A Simple and Performant Baseline for Vision and Language (2019, methodology): “VisualBERT integrates BERT (Devlin et al., 2019), a recent Transformer-based model (Vaswani et al., 2017) for natural language processing, and pre-trained object proposals systems such as Faster-RCNN (Ren et al., 2015) and it can be applied to a variety of vision-and-language tasks.”
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks (2019, methodology): “In general, co-attention for vision-and-language is not a new idea (being first proposed in [31]) and concurrent work [32,33] has shown the effectiveness of similar co-attentional transformer structures on the visual question answering [3] task.”
- Fixing the train-test resolution discrepancy (2019, background): “Convolutional Neural Networks [21] (CNNs) are used extensively in computer vision tasks such as image classification [20], object detection [30], inpainting [41], style transfer [11] and even image compression [31].”
- Learning Representations by Maximizing Mutual Information Across Views (2019, methodology): “Similarly, large convolutional networks pre-trained on large supervised corpora have been widely used to improve performance across the spectrum of computer vision tasks [Donahue et al., 2014, Ren et al., 2015, He et al., 2017, Carreira and Zisserman, 2017].”
- Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, methodology): “When training the network for image detection, we use the Faster-RCNN architecture and loss, without any modification [55]. unsupervised representation learning.”
- Weight Standardization (2019, methodology): “This enables ResNeXt to train with GN in Mask R-CNN [10] and Faster R-CNN [34], which we will discuss in the next subsection.”