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

Segment anything model (SAM) has shown its spectacular performance insegmenting universal objects, especially when elaborate prompts are provided.However, the drawback of SAM is twofold. On the first hand, it fails to segmentspecific targets, e.g., shadow images or lesions in medical images. On theother hand, manually specifying prompts is extremely time-consuming. Toovercome the problems, we propose AdapterShadow, which adapts SAM model forshadow detection. To adapt SAM for shadow images, trainable adapters areinserted into the frozen image encoder of SAM, since the training of the fullSAM model is both time and memory consuming. Moreover, we introduce a novelgrid sampling method to generate dense point prompts, which helps toautomatically segment shadows without any manual interventions. Extensiveexperiments are conducted on four widely used benchmark datasets to demonstratethe superior performance of our proposed method. Codes will are publiclyavailable at https://github.com/LeipingJie/AdapterShadow.

AdapterShadow: Adapting Segment Anything Model for Shadow Detection