• Publications
  • Influence
Deep Residual Learning for Image Recognition
TLDR
We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. Expand
  • 65,687
  • 14355
  • PDF
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
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
  • 23,623
  • 5207
  • PDF
Mask R-CNN
TLDR
We present a conceptually simple, flexible, and general framework for object instance segmentation. Expand
  • 5,794
  • 1402
Feature Pyramid Networks for Object Detection
TLDR
In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. Expand
  • 5,933
  • 1325
  • PDF
Focal Loss for Dense Object Detection
TLDR
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
  • 4,459
  • 933
Identity Mappings in Deep Residual Networks
TLDR
We analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. Expand
  • 4,733
  • 875
  • PDF
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TLDR
We study rectifier neural networks for image classification from two aspects. Expand
  • 9,636
  • 738
  • PDF
Aggregated Residual Transformations for Deep Neural Networks
TLDR
We present a simple, highly modularized network architecture for image classification. Expand
  • 3,618
  • 680
  • PDF
Image Super-Resolution Using Deep Convolutional Networks
TLDR
We propose a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images. Expand
  • 3,660
  • 676
  • PDF
Mask R-CNN
TLDR
We present a conceptually simple, flexible, and general framework for object instance segmentation. Expand
  • 2,980
  • 584
  • PDF
...
1
2
3
4
5
...