2022
DOI: 10.1109/tgrs.2021.3075546
|View full text |Cite
|
Sign up to set email alerts
|

Adaptive Hash Attention and Lower Triangular Network for Hyperspectral Image Classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
16
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9

Relationship

1
8

Authors

Journals

citations
Cited by 17 publications
(16 citation statements)
references
References 63 publications
0
16
0
Order By: Relevance
“…The spatial attention module is made to suppress interference pixels in images and enhance attention to regions of interest 44 . The interference pixels at the edges of HSI patches can negatively impact the expressiveness of the extracted features 53 . The self-attention mechanism is a typical spatial attention module that has recently become well known in image processing.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The spatial attention module is made to suppress interference pixels in images and enhance attention to regions of interest 44 . The interference pixels at the edges of HSI patches can negatively impact the expressiveness of the extracted features 53 . The self-attention mechanism is a typical spatial attention module that has recently become well known in image processing.…”
Section: Related Workmentioning
confidence: 99%
“…44 The interference pixels at the edges of HSI patches can negatively impact the expressiveness of the extracted features. 53 The self-attention mechanism is a typical spatial attention module that has recently become well known in image processing. The self-attention mechanism captures long-range contextual information to obtain discriminative feature representations.…”
Section: Introductionmentioning
confidence: 99%
“…By integrating the SaMLP and SeMLP, discriminative spectral-spatial features can be extracted from HSI cubes. In addition, we adopt the skip connection mechanism of [44] to enhance information exchange between layers, which has been demonstrated to be an effective strategy for modern neural architecture design [45][46][47]. The SaMLP and SeMLP have similar architecture and both consist of two fully connected layers and a non-linear activation, as shown in Figure 4.…”
Section: Ss-mlp Blockmentioning
confidence: 99%
“…To fully explore the discriminant features, Zhan et al innovated a three-direction spectral-spatial convolution neural network to improve the accuracy of change detection [44]. To eliminate redundant information and interclass interference, Ge et al designed an adaptive hash attention and lower triangular network for HSI classification [45]. Although these classification methods can extract deep joint spectral-spatial features, it is still inconvenient for them to focus more on discriminated feature regions and restrain the unnecessary information from plentiful spectral-spatial features.…”
Section: Introductionmentioning
confidence: 99%