Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Conference papers

Where are my clothes? A multi-level approach for evaluating deep instance segmentation architectures on fashion images

Abstract : In this paper we present an extensive evaluation of instance segmentation in the context of images containing clothes. We propose a multi level evaluation that completes the classical overlapping criteria given by IoU. In particular, we quantify both the contour and color content accuracy of the the predicted segmentation masks. We demonstrate that the proposed evaluation framework is relevant to obtain meaningful insights on models performance through experiments conducted on five state of the art instance segmentation methods.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03272473
Contributor : Warren Jouanneau Connect in order to contact the contributor
Submitted on : Monday, June 28, 2021 - 1:46:42 PM
Last modification on : Saturday, June 25, 2022 - 10:43:54 AM
Long-term archiving on: : Wednesday, September 29, 2021 - 7:27:00 PM

File

CVPRW_Fashion_Paper (4).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03272473, version 1

Collections

Citation

Warren Jouanneau, Aurélie Bugeau, Marc Palyart, Nicolas Papadakis, Laurent Vézard. Where are my clothes? A multi-level approach for evaluating deep instance segmentation architectures on fashion images. CVPR Workshop on Computer Vision for Fashion, Art, and Design (CVFAD'21), Jun 2021, Virtual event, United States. pp.3951-3955. ⟨hal-03272473⟩

Share

Metrics

Record views

28

Files downloads

19