• Publications
  • Influence
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
We introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. Expand
  • 23,149
  • 5153
  • PDF
Fast R-CNN
  • Ross B. Girshick
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 29 April 2015
This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Expand
  • 10,709
  • 2268
  • PDF
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
We propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
  • 13,381
  • 1978
  • PDF
You Only Look Once: Unified, Real-Time Object Detection
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem toExpand
  • 11,308
  • 1687
  • PDF
Caffe: Convolutional Architecture for Fast Feature Embedding
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. Expand
  • 12,712
  • 1649
  • PDF
Object Detection with Discriminatively Trained Part Based Models
We describe an object detection system based on mixtures of multiscale deformable part models that achieves state-of-the-art results in the PASCAL object detection challenges. Expand
  • 8,735
  • 1414
  • PDF
Mask R-CNN
We present a conceptually simple, flexible, and general framework for object instance segmentation. Expand
  • 5,582
  • 1329
Feature Pyramid Networks for Object Detection
In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. Expand
  • 5,789
  • 1292
  • PDF
Focal Loss for Dense Object Detection
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. Expand
  • 4,291
  • 892
Aggregated Residual Transformations for Deep Neural Networks
We present a simple, highly modularized network architecture for image classification. Expand
  • 3,533
  • 668
  • PDF