PaperNeurIPS 2015 · 2015
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1page built on it
3more pages cite it
2narratives
6registry papers cite it
In the Atlas
ModelPrimary source of
Faster R-CNN
Two-stage CNN object detector that replaces external Selective Search / EdgeBoxes proposals with a learned Region Proposal Network sharing conv features with the Fast R-CNN head — yielding near-real-time multi-class detection on GPU (5 fps with VGG-16) and ImageNet-pretrained backbones swapped freely from ZF through ResNet-101.
Cited as a reference by 3 pages, grouped by domain
Detection 2
Segmentation 1
Appears in 2 narratives
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 6
Builds on · 2
2012ImageNet Classification with Deep Convolutional Neural NetworksKrizhevsky, Sutskever, Hinton2015Fully Convolutional Networks for Semantic SegmentationLong, Shelhamer, DarrellBuilt upon by · 6
2016You Only Look Once: Unified, Real-Time Object DetectionRedmon, Divvala et al.2017Feature Pyramid Networks for Object DetectionLin, Dollár et al.2017Focal Loss for Dense Object DetectionLin, Goyal et al.2018MobileNetV2: Inverted Residuals and Linear BottlenecksSandler, Howard et al.2019Momentum Contrast for Unsupervised Visual Representation LearningHe, Fan et al.2020Bootstrap your own latent: A new approach to self-supervised LearningGrill, Strub et al.