Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/135012
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTian, Z.-
dc.contributor.authorShen, C.-
dc.contributor.authorChen, H.-
dc.contributor.authorHe, T.-
dc.date.issued2022-
dc.identifier.citationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022; 44(4):1922-1933-
dc.identifier.issn0162-8828-
dc.identifier.issn1939-3539-
dc.identifier.urihttps://hdl.handle.net/2440/135012-
dc.description.abstractIn computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the pre-defined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating the intersection over union (IoU) scores during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at: git:io=AdelaiDet-
dc.description.statementofresponsibilityZhi Tian, Chunhua Shen, Hao Chen, and Tong He-
dc.language.isoen-
dc.publisherInstitute of Electrical and Electronics Engineers-
dc.rights© 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.-
dc.source.urihttp://dx.doi.org/10.1109/tpami.2020.3032166-
dc.subjectObject detection; fully convolutional one-stage object detection; anchor box; deep learning-
dc.titleFCOS: A Simple and Strong Anchor-Free Object Detector-
dc.typeJournal article-
dc.identifier.doi10.1109/TPAMI.2020.3032166-
dc.relation.granthttp://purl.org/au-research/grants/arc/DP200103797-
pubs.publication-statusPublished-
dc.identifier.orcidTian, Z. [0000-0002-6196-2655]-
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.