2022
DOI: 10.1016/j.asoc.2022.108419
|View full text |Cite
|
Sign up to set email alerts
|

Multi-scale Sparse Network with Cross-Attention Mechanism for image-based butterflies fine-grained classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
10

Relationship

1
9

Authors

Journals

citations
Cited by 19 publications
(6 citation statements)
references
References 31 publications
0
6
0
Order By: Relevance
“…At the same time, in the process of construction, the relationship between ideas and educational systems should be clearly divided. [14] is a mechanism that enhances the Encoder + Decoder model's performance by taking into account how people typically observe things. Machine translation was carried out while aligning the source languages, which clearly improved the performance of the neural network machine translation model.…”
Section: Related Workmentioning
confidence: 99%
“…At the same time, in the process of construction, the relationship between ideas and educational systems should be clearly divided. [14] is a mechanism that enhances the Encoder + Decoder model's performance by taking into account how people typically observe things. Machine translation was carried out while aligning the source languages, which clearly improved the performance of the neural network machine translation model.…”
Section: Related Workmentioning
confidence: 99%
“…In supervised classification [26], the categories of known patterns and the category attributes of some samples are first learned or trained with samples with category labels, so that the classification system can correctly classify these known samples and then use. A learned classification system classifies unknown samples.…”
Section: Integration and Utilization Of Universitymentioning
confidence: 99%
“…To solve the problem of unfocused semantic features, M. Li et al. (2022) proposed a three‐directional cross‐attention mechanism (CAM). To cooperate the feature extraction of multi‐scale with two‐channel convolutional networks, Zhang et al.…”
Section: Introductionmentioning
confidence: 99%