%0 Journal Article %T Logo Detection With No Priors %A Diego Velazquez %A Josep M. Gonfaus %A Pau Rodriguez %A Xavier Roca %A Seiichi Ozawa %A Jordi Gonzalez %J IEEE Access %D 2021 %V 9 %F Diego Velazquez2021 %O ISE %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3664), last updated on Thu, 15 Sep 2022 10:21:46 +0200 %X 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. %U https://ieeexplore.ieee.org/document/9502074 %U http://dx.doi.org/10.1109/ACCESS.2021.3101297 %P 106998-107011