On Pre-Trained Image Features and Synthetic Images for Deep Learning

10/29/2017
by   Stefan Hinterstoisser, et al.
0

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the labeling comes for free, and several approaches have been proposed to combine synthetic and real images for training. In this paper, we show that a simple trick is sufficient to train very effectively modern object detectors with synthetic images only: We freeze the layers responsible for feature extraction to generic layers pre-trained on real images, and train only the remaining layers with plain OpenGL rendering. Our experiments with very recent deep architectures for object recognition (Faster-RCNN, R-FCN, Mask-RCNN) and image feature extractors (InceptionResnet and Resnet) show this simple approach performs surprisingly well.

READ FULL TEXT

page 1

page 4

page 5

page 7

page 8

research
09/09/2019

Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum

ImageNet pre-training has been regarded as essential for training accura...
research
02/26/2019

An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection

Deep learning methods typically require vast amounts of training data to...
research
06/16/2021

Toward Robotic Weed Control: Detection of Nutsedge Weed in Bermudagrass Turf Using Inaccurate and Insufficient Training Data

To enable robotic weed control, we develop algorithms to detect nutsedge...
research
11/28/2014

On Rendering Synthetic Images for Training an Object Detector

We propose a novel approach to synthesizing images that are effective fo...
research
04/01/2022

Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes

Learning on synthetic data and transferring the resulting properties to ...
research
03/29/2019

Training Object Detectors on Synthetic Images Containing Reflecting Materials

One of the grand challenges of deep learning is the requirement to obtai...
research
11/11/2020

Where to drive: free space detection with one fisheye camera

The development in the field of autonomous driving goes hand in hand wit...

Please sign up or login with your details

Forgot password? Click here to reset