Improving Object Detection in Art Images Using Only Style Transfer

02/12/2021
by   David Kadish, et al.
0

Despite recent advances in object detection using deep learning neural networks, these neural networks still struggle to identify objects in art images such as paintings and drawings. This challenge is known as the cross depiction problem and it stems in part from the tendency of neural networks to prioritize identification of an object's texture over its shape. In this paper we propose and evaluate a process for training neural networks to localize objects - specifically people - in art images. We generate a large dataset for training and validation by modifying the images in the COCO dataset using AdaIn style transfer. This dataset is used to fine-tune a Faster R-CNN object detection network, which is then tested on the existing People-Art testing dataset. The result is a significant improvement on the state of the art and a new way forward for creating datasets to train neural networks to process art images.

READ FULL TEXT

page 4

page 6

page 7

research
12/21/2022

Artistic Arbitrary Style Transfer

Arbitrary Style Transfer is a technique used to produce a new image from...
research
08/03/2022

Style Transfer of Black and White Silhouette Images using CycleGAN and a Randomly Generated Dataset

CycleGAN can be used to transfer an artistic style to an image. It does ...
research
03/28/2018

Deep Learning Object Detection Methods for Ecological Camera Trap Data

Deep learning methods for computer vision tasks show promise for automat...
research
04/26/2023

From Chaos Comes Order: Ordering Event Representations for Object Detection

Today, state-of-the-art deep neural networks that process events first c...
research
02/27/2020

Improving Learning Effectiveness For Object Detection and Classification in Cluttered Backgrounds

Usually, Neural Networks models are trained with a large dataset of imag...
research
09/04/2019

Aerial multi-object tracking by detection using deep association networks

A lot a research is focused on object detection and it has achieved sign...
research
10/27/2016

Detecting People in Artwork with CNNs

CNNs have massively improved performance in object detection in photogra...

Please sign up or login with your details

Forgot password? Click here to reset