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

Computer vision is often performed using Convolutional Neural Networks(CNNs). CNNs are compute-intensive and challenging to deploy onpower-contrained systems such as mobile and Internet-of-Things (IoT) devices.CNNs are compute-intensive because they indiscriminately compute many featureson all pixels of the input image. We observe that, given a computer visiontask, images often contain pixels that are irrelevant to the task. For example,if the task is looking for cars, pixels in the sky are not very useful.Therefore, we propose that a CNN be modified to only operate on relevant pixelsto save computation and energy. We propose a method to study three popularcomputer vision datasets, finding that 48% of pixels are irrelevant. We alsopropose the focused convolution to modify a CNN's convolutional layers toreject the pixels that are marked irrelevant. On an embedded device, we observeno loss in accuracy, while inference latency, energy consumption, andmultiply-add count are all reduced by about 45%.

Irrelevant Pixels are Everywhere: Find and Exclude Them for More Efficient Computer Vision