English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the realm of artificial intelligence, the emergence of foundation models,backed by high computing capabilities and extensive data, has beenrevolutionary. Segment Anything Model (SAM), built on the Vision Transformer(ViT) model with millions of parameters and vast training dataset SA-1B, excelsin various segmentation scenarios relying on its significance of semanticinformation and generalization ability. Such achievement of visual foundationmodel stimulates continuous researches on specific downstream tasks in computervision. The ClassWise-SAM-Adapter (CWSAM) is designed to adapt thehigh-performing SAM for landcover classification on space-borne SyntheticAperture Radar (SAR) images. The proposed CWSAM freezes most of SAM'sparameters and incorporates lightweight adapters for parameter efficientfine-tuning, and a classwise mask decoder is designed to achieve semanticsegmentation task. This adapt-tuning method allows for efficient landcoverclassification of SAR images, balancing the accuracy with computational demand.In addition, the task specific input module injects low frequency informationof SAR images by MLP-based layers to improve the model performance. Compared toconventional state-of-the-art semantic segmentation algorithms by extensiveexperiments, CWSAM showcases enhanced performance with fewer computingresources, highlighting the potential of leveraging foundational models likeSAM for specific downstream tasks in the SAR domain. The source code isavailable at: https://github.com/xypu98/CWSAM.

ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation