Logo Detection with No Priors
Velazquez Dorta, Diego Alejandro (Centre de Visió per Computador)
Gonfaus, Josep M. (Servei de Tractament d'Imatges)
Rodríguez López, Pau (Element AI)
Roca, F. Xavier (Centre de Visió per Computador)
Ozawa, Seiichi (Kobe University. Center for Mathematical and Data Sciences)
Gonzàlez, Jordi (Centre de Visió per Computador)

Date:	2021
Description:	14 pàg.
Abstract:	In recent years, top referred methods on object detection like R-CNN have implemented this task as a combination of proposal region generation and supervised classification on the proposed bounding boxes. Although this pipeline has achieved state-of-the-art results in multiple datasets, it has inherent limitations that make object detection a very complex and inefficient task in computational terms. Instead of considering this standard strategy, in this paper we enhance Detection Transformers (DETR) which tackles object detection as a set-prediction problem directly in an end-to-end fully differentiable pipeline without requiring priors. In particular, we incorporate Feature Pyramids (FP) to the DETR architecture and demonstrate the effectiveness of the resulting DETR-FP approach on improving logo detection results thanks to the improved detection of small logos. So, without requiring any domain specific prior to be fed to the model, DETR-FP obtains competitive results on the OpenLogo and MS-COCO datasets offering a relative improvement of up to 30%, when compared to a Faster R-CNN baseline which strongly depends on hand-designed priors.
Grants:	Generalitat de Catalunya 2020/DI62 Ministerio de Economía y Competitividad TIN2015-65464-R Agencia Estatal de Investigación PID2020-120311RB-I00
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	Attention ; Deep learning ; Logo detection ; Object detection ; Transformers
Published in:	IEEE Access, Vol. 9 (July 2021) , p. 106998-107011, ISSN 2169-3536

DOI: 10.1109/ACCESS.2021.3101297

14 p, 4.0 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles