2019
DOI: 10.48550/arxiv.1901.00303
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 33 publications
0
1
0
Order By: Relevance
“…X-ray and thermal security images, on the other hand, lack the fine detail found in nature photography and have a restricted color spectrum, as well as low contrast and roughness. The presence of object overlap in these pictures distinguishes them, posing a challenge to deep learning models since object overlap increases intra-class differences as discussed in [2]. Because each pixel represents a muted radiation intensity that may be viewed in an image, pixels in security images convey information about object overlap.…”
Section: Introductionmentioning
confidence: 99%
“…X-ray and thermal security images, on the other hand, lack the fine detail found in nature photography and have a restricted color spectrum, as well as low contrast and roughness. The presence of object overlap in these pictures distinguishes them, posing a challenge to deep learning models since object overlap increases intra-class differences as discussed in [2]. Because each pixel represents a muted radiation intensity that may be viewed in an image, pixels in security images convey information about object overlap.…”
Section: Introductionmentioning
confidence: 99%