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 is a promising alternative to alleviate the issue of highannotation cost in the computer vision tasks by consciously selecting moreinformative samples to label. Active learning for object detection is morechallenging and existing efforts on it are relatively rare. In this paper, wepropose a novel hybrid approach to address this problem, where theinstance-level uncertainty and diversity are jointly considered in a bottom-upmanner. To balance the computational complexity, the proposed approach isdesigned as a two-stage procedure. At the first stage, an Entropy-basedNon-Maximum Suppression (ENMS) is presented to estimate the uncertainty ofevery image, which performs NMS according to the entropy in the feature spaceto remove predictions with redundant information gains. At the second stage, adiverse prototype (DivProto) strategy is explored to ensure the diversityacross images by progressively converting it into the intra-class andinter-class diversities of the entropy-based class-specific prototypes.Extensive experiments are conducted on MS COCO and Pascal VOC, and the proposedapproach achieves state of the art results and significantly outperforms theother counterparts, highlighting its superiority.

Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint