2021
DOI: 10.48550/arxiv.2104.08381
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Abstract: Building reliable object detectors that are robust to domain shifts, such as various changes in context, viewpoint, and object appearances, is critical for real-world applications. In this work, we study the effectiveness of auxiliary self-supervised tasks to improve out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf), which operates on the region features of the object… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Publication Types

Select...

Relationship

0
0

Authors

Journals

citations
Cited by 0 publications
references
References 36 publications
0
0
0
Order By: Relevance

No citations

Set email alert for when this publication receives citations?