R-CNN minus R

06/23/2015
by   Karel Lenc, et al.
0

Deep convolutional neural networks (CNNs) have had a major impact in most areas of image understanding, including object category detection. In object detection, methods such as R-CNN have obtained excellent results by integrating CNNs with region proposal generation algorithms such as selective search. In this paper, we investigate the role of proposal generation in CNN-based detectors in order to determine whether it is a necessary modelling component, carrying essential geometric information not contained in the CNN, or whether it is merely a way of accelerating detection. We do so by designing and evaluating a detector that uses a trivial region generation scheme, constant for each image. Combined with SPP, this results in an excellent and fast detector that does not require to process an image with algorithms other than the CNN itself. We also streamline and simplify the training of CNN-based detectors by integrating several learning steps in a single algorithm, as well as by proposing a number of improvements that accelerate detection.

READ FULL TEXT

page 1

page 5

research
04/16/2016

Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

In CNN-based object detection methods, region proposal becomes a bottlen...
research
01/25/2016

Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection

R-CNN style methods are sorts of the state-of-the-art object detection m...
research
09/11/2018

CNN-Based Signal Detection for Banded Linear Systems

Banded linear systems arise in many communication scenarios, e.g., those...
research
06/20/2017

Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer

The main goal of this paper is to analyze the general problem of using C...
research
09/23/2019

Improving CNN-based Planar Object Detection with Geometric Prior Knowledge

In this paper, we focus on the question: how might mobile robots take ad...
research
03/24/2021

Object Localization Through a Single Multiple-Model Convolutional Neural Network with a Specific Training Approach

Object localization has a vital role in any object detector, and therefo...
research
05/26/2015

Accelerating Very Deep Convolutional Networks for Classification and Detection

This paper aims to accelerate the test-time computation of convolutional...

Please sign up or login with your details

Forgot password? Click here to reset