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 recent years, the success of large-scale vision-language models (VLMs)such as CLIP has led to their increased usage in various computer vision tasks.These models enable zero-shot inference through carefully crafted instructionaltext prompts without task-specific supervision. However, the potential of VLMsfor generalization tasks in remote sensing (RS) has not been fully realized. Toaddress this research gap, we propose a novel image-conditioned prompt learningstrategy called the Visual Attention Parameterized Prompts Learning Network(APPLeNet). APPLeNet emphasizes the importance of multi-scale feature learningin RS scene classification and disentangles visual style and content primitivesfor domain generalization tasks. To achieve this, APPLeNet combines visualcontent features obtained from different layers of the vision encoder and styleproperties obtained from feature statistics of domain-specific batches. Anattention-driven injection module is further introduced to generate visualtokens from this information. We also introduce an anti-correlation regularizerto ensure discrimination among the token embeddings, as this visual informationis combined with the textual tokens. To validate APPLeNet, we curated fouravailable RS benchmarks and introduced experimental protocols and datasets forthree domain generalization tasks. Our results consistently outperform therelevant literature and code is available athttps://github.com/mainaksingha01/APPLeNet

APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIP