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 energy consumption of deep learning models is increasing at abreathtaking rate, which raises concerns due to potential negative effects oncarbon neutrality in the context of global warming and climate change. With theprogress of efficient deep learning techniques, e.g., model compression,researchers can obtain efficient models with fewer parameters and smallerlatency. However, most of the existing efficient deep learning methods do notexplicitly consider energy consumption as a key performance indicator.Furthermore, existing methods mostly focus on the inference costs of theresulting efficient models, but neglect the notable energy consumptionthroughout the entire life cycle of the algorithm. In this paper, we presentthe first large-scale energy consumption benchmark for efficient computervision models, where a new metric is proposed to explicitly evaluate thefull-cycle energy consumption under different model usage intensity. Thebenchmark can provide insights for low carbon emission when selecting efficientdeep learning algorithms in different model usage scenarios.

Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision