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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The increasing availability and accessibility of numerous overhead imagesallows us to estimate and assess the spatial arrangement of groups ofgeospatial target objects, which can benefit many applications, such as trafficmonitoring and agricultural monitoring. Spatial arrangement estimation is theprocess of identifying the areas which contain the desired objects in overheadimages. Traditional supervised object detection approaches can estimateaccurate spatial arrangement but require large amounts of bounding boxannotations. Recent semi-supervised clustering approaches can reduce manuallabeling but still require annotations for all object categories in the image.This paper presents the target-guided generative model (TGGM), under theVariational Auto-encoder (VAE) framework, which uses Gaussian Mixture Models(GMM) to estimate the distributions of both hidden and decoder variables inVAE. Modeling both hidden and decoder variables by GMM reduces the requiredmanual annotations significantly for spatial arrangement estimation. Unlikeexisting approaches that the training process can only update the GMM as awhole in the optimization iterations (e.g., a "minibatch"), TGGM allows theupdate of individual GMM components separately in the same optimizationiteration. Optimizing GMM components separately allows TGGM to exploit thesemantic relationships in spatial data and requires only a few labels toinitiate and guide the generative process. Our experiments shows that TGGMachieves results comparable to the state-of-the-art semi-supervised methods andoutperforms unsupervised methods by 10% based on the $F_{1}$ scores, whilerequiring significantly fewer labeled data.

Guided Generative Models using Weak Supervision for Detecting Object Spatial Arrangement in Overhead Images