The MAMe Dataset: On the relevance of High Resolution and Variable Shape image properties

09/29/2021
by   dariogarcia, et al.
0

In the image classification task, the most common approach is to resize all images in a dataset to a unique shape, while reducing their precision to a size which facilitates experimentation at scale. This practice has benefits from a computational perspective, but it entails negative side-effects on performance due to loss of information and image deformation. In this work we introduce the MAMe dataset, an image classification dataset with remarkable high resolution and variable shape properties. The goal of MAMe is to provide a tool for studying the impact of such properties in image classification, while motivating research in the field. The MAMe dataset contains thousands of artworks from three different museums, and proposes a classification task consisting on differentiating between 29 mediums (i.e. materials and techniques) supervised by art experts. After reviewing the singularity of MAMe in the context of current image classification tasks, a thorough description of the task is provided, together with dataset statistics. Experiments are conducted to evaluate the impact of using high resolution images, variable shape inputs and both properties at the same time. Results illustrate the positive impact in performance when using high resolution images, while highlighting the lack of solutions to exploit variable shapes. An additional experiment exposes the distinctiveness between the MAMe dataset and the prototypical ImageNet dataset. Finally, the baselines are inspected using explainability methods and expert knowledge, to gain insights on the challenges that remain ahead.

READ FULL TEXT

page 4

page 10

page 15

page 16

page 17

page 18

page 19

page 20

research
07/27/2020

A Closer Look at Art Mediums: The MAMe Image Classification Dataset

Art is an expression of human creativity, skill and technology. An excep...
research
11/20/2019

MetH: A family of high-resolution and variable-shape image challenges

High-resolution and variable-shape images have not yet been properly add...
research
04/11/2016

Binarized Neural Networks on the ImageNet Classification Task

We trained Binarized Neural Networks (BNNs) on the high resolution Image...
research
12/27/2016

An Automated CNN Recommendation System for Image Classification Tasks

Nowadays the CNN is widely used in practical applications for image clas...
research
12/04/2022

Kernel Inversed Pyramidal Resizing Network for Efficient Pavement Distress Recognition

Pavement Distress Recognition (PDR) is an important step in pavement ins...
research
04/26/2023

ZRG: A High Resolution 3D Residential Rooftop Geometry Dataset for Machine Learning

In this paper we present the Zeitview Rooftop Geometry (ZRG) dataset. ZR...
research
06/15/2018

Recurrent Multiresolution Convolutional Networks for VHR Image Classification

Classification of very high resolution (VHR) satellite images has three ...

Please sign up or login with your details

Forgot password? Click here to reset