The classical Feature Pyramid Network often results in the neglect of detail information due to information downsampling. Furthermore, the context dependency of the input area is homogeneous, which limits the accuracy of image segmentation. To solve the above issues, this article proposes a novel Feature Pyramid Network by incorporating feature complementarity and a linear attention mechanism. Reweighing single-scale features in grid fusion, the network utilizes cross-scale complementary knowledge to decrease the neglect of local details in the image. Additionally, a linear attention mechanism with a differentiable linear unit kernel function is leveraged to enhance the long-range pixel associations across the global image scope. This mechanism adaptively allocates attention weights with a lightweight structure, especially emphasizing critical information such as object boundaries for the enhancement of the proposed model's accuracy and robustness. After testing, the overall accuracy of segmentation is up to 92.7% and 92.9%, respectively, which proves that the proposed method can significantly improve the segmentation performance.
In the hyperspectral imaging field, denoising is not only a fundamental issue in image processing but also an essential preprocessing step. In recent years, denoising models have introduced various spatial single factor regularizations to characterize their spatial priors. However, these models do not fully leverage the commonalities and spectral continuity across different bands of hyperspectral images (HSI). To address this, we propose a low-rank tensor decomposition algorithm incorporating a two-factor regularization constraint on the dimensionality reduction factor. This model captures the global low-rank nature of the spectrum, while weighted group sparse constraints are imposed on the spatial factors to enhance the group sparsity of the HSI. Additionally, continuity constraints on the spectral factors are introduced to promote the spectral continuity of the HSI. The model is further refined by employing a logarithmic low-rank function to constrain the coefficient tensor. Moreover, we develop a proximal alternating minimization (PAM) algorithm and the algorithm of alternating direction multiplication (ADMM) is used to solve this model. Extensive experiments demonstrate that our method surpasses other existing HSI denoising techniques and exhibits superior performance in mixed noise removal.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.