Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Reducing Label Noise in Anchor-Free Object Detection
Date
2020-01-01
Author
Samet, Nermin
Hicsonmez, Samet
Akbaş, Emre
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
2
views
0
downloads
Cite This
Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled features may be on the background or an occluder object, or they are simply not discriminative features. In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors. We sum-pool predictions stemming from individual features into a single prediction. This allows the model to reduce the contributions of non-discriminatory features during training. We develop a new one-stage, anchor-free object detector, PPDet, to employ this labeling strategy during training and a similar prediction pooling method during inference. On the COCO dataset, PPDet achieves the best performance among anchor-free top-down detectors and performs on-par with the other state-of-the-art methods. It also outperforms all major one-stage and two-stage methods in small object detection (APS 31.4). Code is available at https://github.com/nerminsamet/ppdet.
URI
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85117584856&origin=inward
https://hdl.handle.net/11511/106745
Conference Name
31st British Machine Vision Conference, BMVC 2020
Collections
Department of Computer Engineering, Conference / Seminar
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
N. Samet, S. Hicsonmez, and E. Akbaş, “Reducing Label Noise in Anchor-Free Object Detection,” presented at the 31st British Machine Vision Conference, BMVC 2020, Virtual, Online, 2020, Accessed: 00, 2023. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85117584856&origin=inward.