Grid R-CNN

11/29/2018
by   Xin Lu, et al.
14

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection. Different from the traditional regression based methods, the Grid R-CNN captures the spatial information explicitly and enjoys the position sensitive property of fully convolutional architecture. Instead of using only two independent points, we design a multi-point supervision formulation to encode more clues in order to reduce the impact of inaccurate prediction of specific points. To take the full advantage of the correlation of points in a grid, we propose a two-stage information fusion strategy to fuse feature maps of neighbor grid points. The grid guided localization approach is easy to be extended to different state-of-the-art detection frameworks. Grid R-CNN leads to high quality object localization, and experiments demonstrate that it achieves a 4.1 benchmark compared to Faster R-CNN with Res50 backbone and FPN architecture.

READ FULL TEXT

page 4

page 8

research
06/13/2019

Grid R-CNN Plus: Faster and Better

Grid R-CNN is a well-performed objection detection framework. It transfo...
research
03/07/2020

CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

In object detection, offset-guided and point-guided regression dominate ...
research
07/21/2020

BorderDet: Border Feature for Dense Object Detection

Dense object detectors rely on the sliding-window paradigm that predicts...
research
04/22/2021

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation

This paper proposes a novel heterogeneous grid convolution that builds a...
research
07/21/2023

Redemption from Range-view for Accurate 3D Object Detection

Most recent approaches for 3D object detection predominantly rely on poi...
research
09/06/2021

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

We present a flexible and high-performance framework, named Pyramid R-CN...
research
02/11/2019

S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition

We present a novel event recognition approach called Spatially-preserved...

Please sign up or login with your details

Forgot password? Click here to reset