2020
DOI: 10.48550/arxiv.2012.13763
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Balance-Oriented Focal Loss with Linear Scheduling for Anchor Free Object Detection

Abstract: Most existing object detectors suffer from class imbalance problems that hinder balanced performance. In particular, anchor free object detectors have to solve the background imbalance problem due to detection in a per-pixel prediction fashion as well as foreground imbalance problem simultaneously. In this work, we propose Balance-oriented focal loss that can induce balanced learning by considering both background and foreground balance comprehensively. This work aims to address imbalance problem in the situat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 28 publications
0
1
0
Order By: Relevance
“…Additionally, a focal loss term [24,25] was used for the breath detection task, and a convex mixture of all the losses after dynamic weight averaging [26], with weighting factor λ, was used as the MTL loss to train the network shown in Figure 5.…”
Section: B Acoustic Modelingmentioning
confidence: 99%
“…Additionally, a focal loss term [24,25] was used for the breath detection task, and a convex mixture of all the losses after dynamic weight averaging [26], with weighting factor λ, was used as the MTL loss to train the network shown in Figure 5.…”
Section: B Acoustic Modelingmentioning
confidence: 99%