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

Despite the blooming success of architecture search for vision tasks inresource-constrained environments, the design of on-device object detectionarchitectures have mostly been manual. The few automated search efforts areeither centered around non-mobile-friendly search spaces or not guided byon-device latency. We propose MnasFPN, a mobile-friendly search space for thedetection head, and combine it with latency-aware architecture search toproduce efficient object detection models. The learned MnasFPN head, whenpaired with MobileNetV2 body, outperforms MobileNetV3+SSDLite by 1.8 mAP atsimilar latency on Pixel. It is also both 1.0 mAP more accurate and 10% fasterthan NAS-FPNLite. Ablation studies show that the majority of the performancegain comes from innovations in the search space. Further explorations reveal aninteresting coupling between the search space design and the search algorithm,and that the complexity of MnasFPN search space may be at a local optimum.

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices