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

The performance of face detectors has been largely improved with thedevelopment of convolutional neural network. However, it remains challengingfor face detectors to detect tiny, occluded or blurry faces. Besides, most facedetectors can't locate face's position precisely and can't achieve highIntersection-over-Union (IoU) scores. We assume that problems inside areinadequate use of supervision information and imbalance between semantics anddetails at all level feature maps in CNN even with Feature Pyramid Networks(FPN). In this paper, we present a novel single-shot face detection network,named DF$^2$S$^2$ (Detection with Feature Fusion and Segmentation Supervision),which introduces a more effective feature fusion pyramid and a more efficientsegmentation branch on ResNet-50 to handle mentioned problems. Specifically,inspired by FPN and SENet, we apply semantic information from higher-levelfeature maps as contextual cues to augment low-level feature maps via a spatialand channel-wise attention style, preventing details from being covered by toomuch semantics and making semantics and details complement each other. Wefurther propose a semantic segmentation branch to best utilize detectionsupervision information meanwhile applying attention mechanism in aself-supervised manner. The segmentation branch is supervised by weaksegmentation ground-truth (no extra annotation is required) in a hierarchicalmanner, deprecated in the inference time so it wouldn't compromise theinference speed. We evaluate our model on WIDER FACE dataset and achievedstate-of-art results.

Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision