G-CNN: an Iterative Grid Based Object Detector

12/24/2015
by   Mahyar Najibi, et al.
0

We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.

READ FULL TEXT

page 3

page 7

page 8

research
12/06/2018

Tube-CNN: Modeling temporal evolution of appearance for object detection in video

Object detection in video is crucial for many applications. Compared to ...
research
11/21/2022

NeRF-RPN: A general framework for object detection in NeRFs

This paper presents the first significant object detection framework, Ne...
research
12/02/2021

Open-set 3D Object Detection

3D object detection has been wildly studied in recent years, especially ...
research
05/04/2022

Dynamic Sparse R-CNN

Sparse R-CNN is a recent strong object detection baseline by set predict...
research
10/15/2019

IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector

It is hard to detect on-road objects under various lighting conditions. ...
research
06/28/2017

Yes-Net: An effective Detector Based on Global Information

This paper introduces a new real-time object detection approach named Ye...
research
04/19/2021

TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases

While common image object detection tasks focus on bounding boxes or seg...

Please sign up or login with your details

Forgot password? Click here to reset