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

Active learning aims to reduce labeling costs by selecting only the mostinformative samples on a dataset. Few existing works have addressed activelearning for object detection. Most of these methods are based on multiplemodels or are straightforward extensions of classification methods, henceestimate an image's informativeness using only the classification head. In thispaper, we propose a novel deep active learning approach for object detection.Our approach relies on mixture density networks that estimate a probabilisticdistribution for each localization and classification head's output. Weexplicitly estimate the aleatoric and epistemic uncertainty in a single forwardpass of a single model. Our method uses a scoring function that aggregatesthese two types of uncertainties for both heads to obtain every image'sinformativeness score. We demonstrate the efficacy of our approach in PASCALVOC and MS-COCO datasets. Our approach outperforms single-model based methodsand performs on par with multi-model based methods at a fraction of thecomputing cost.

Active Learning for Deep Object Detection via Probabilistic Modeling