Feature Pyramid Networks for Object Detection | VitaVision
PaperCVPR · 2017

Feature Pyramid Networks for Object Detection

Tsung-Yi LinPiotr DollárRoss GirshickKaiming HeBharath HariharanSerge Belongie
arXiv 1612.03144DOIView in graph
1page built on it
2more pages cite it
2narratives
0registry papers cite it

In the Atlas

ModelPrimary source of
Feature Pyramid Network (FPN)

Builds a multi-scale feature pyramid inside a single-scale CNN via a top-down pathway with lateral connections, giving every level strong semantics at a fraction of the cost of image pyramids; drives RPN and Fast R-CNN heads per level.

Cited as a reference by 2 pages, grouped by domain

Segmentation 2
Mask R-CNNPointRend

Appears in 2 narratives

NarrativeDetection, Removing the MachineryNarrativeSegmentation, from Energy to Prompt

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 0
’04’05’06’07’08’09’10’11’12’13’14’15’16’17Distinctive Image Features from Scale-Invariant Keypoints (2004)Histograms of Oriented Gradients for Human Detection (2005)Object Detection with Discriminatively Trained Part-Based Models (2010)Fully Convolutional Networks for Semantic Segmentation (2015)Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015)U-Net: Convolutional Networks for Biomedical Image Segmentation (2015)Deep Residual Learning for Image Recognition (2016)Mask R-CNN (2017)
Built upon by · 0