BibTex format
@unpublished{Bonde:2020,
author = {Bonde, U and Alcantarilla, PF and Leutenegger, S},
publisher = {arXiv},
title = {Towards bounding-box free panoptic segmentation},
url = {http://arxiv.org/abs/2002.07705v2},
year = {2020}
}
Publications
Citation
RIS format (EndNote, RefMan)
TY - UNPB
AB - In this work we introduce a new bounding-box free network (BBFNet) forpanoptic segmentation. Panoptic segmentation is an ideal problem for abounding-box free approach as it already requires per-pixel semantic classlabels. We use this observation to exploit class boundaries from anoff-the-shelf semantic segmentation network and refine them to predict instancelabels. Towards this goal BBFNet predicts coarse watershed levels and use it todetect large instance candidates where boundaries are well defined. For smallerinstances, whose boundaries are less reliable, BBFNet also predicts instancecenters by means of Hough voting followed by mean-shift to reliably detectsmall objects. A novel triplet loss network helps merging fragmented instanceswhile refining boundary pixels. Our approach is distinct from previous works inpanoptic segmentation that rely on a combination of a semantic segmentationnetwork with a computationally costly instance segmentation network based onbounding boxes, such as Mask R-CNN, to guide the prediction of instance labelsusing a Mixture-of-Expert (MoE) approach. We benchmark our non-MoE method onCityscapes and Microsoft COCO datasets and show competitive performance withother MoE based approaches while outperfroming exisiting non-proposal basedapproaches. We achieve this while been computationally more efficient in termsof number of parameters and FLOPs. Video results are provided herehttps://blog.slamcore.com/reducing-the-cost-of-understanding.
AU - Bonde,U
AU - Alcantarilla,PF
AU - Leutenegger,S
PB - arXiv
PY - 2020///
TI - Towards bounding-box free panoptic segmentation
UR - http://arxiv.org/abs/2002.07705v2
UR - http://hdl.handle.net/10044/1/79814
ER -