From TrashCan to UNO: Deriving an Underwater Image Dataset To Get a More Consistent and Balanced Version - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2023

From TrashCan to UNO: Deriving an Underwater Image Dataset To Get a More Consistent and Balanced Version

Cyril Barrelet
  • Function : Author
  • PersonId : 1174959
Marc Chaumont
Gérard Subsol
Vincent Creuze

Abstract

The multiplication of publicly available datasets makes it possible to develop Deep Learning models for many real-world applications. However, some domains are still poorly explored, and their related datasets are often small or inconsistent. In addition, some biases linked to the dataset construction or labeling may give the impression that a model is particularly efficient. Therefore, evaluating a model requires a clear understanding of the database. Moreover, a model often reflects a given dataset's performance and may deteriorate if a shift exists between the training dataset and real-world data. In this paper, we derive a more consistent and balanced version of the TrashCan [6] image dataset, called UNO, to evaluate models for detecting non-natural objects in the underwater environment. We propose a method to balance the number of annotations and images for cross-evaluation. We then compare the performance of a SOTA object detection model when using TrashCAN and UNO datasets. Additionally, we assess covariate shift by testing the model on an image dataset for real-world application. Experimental results show significantly better and more consistent performance using the UNO dataset.
Fichier principal
Vignette du fichier
CVAUI2022_ICPR2022_Barrelet_Chaumont_Subsol_Creuze_Gouttefarde_From_TrashCan_to_UNO.pdf (3.94 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

lirmm-03815628 , version 1 (14-10-2022)

Identifiers

Cite

Cyril Barrelet, Marc Chaumont, Gérard Subsol, Vincent Creuze, Marc Gouttefarde. From TrashCan to UNO: Deriving an Underwater Image Dataset To Get a More Consistent and Balanced Version. CVAUI 2022 - 5th Workshop on Computer Vision for Analysis of Underwater Imagery @ICPR, Jul 2022, Montreal, Canada. pp.403-414, ⟨10.1007/978-3-031-37731-0_30⟩. ⟨lirmm-03815628⟩
90 View
85 Download

Altmetric

Share

Gmail Facebook X LinkedIn More