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/

Zendy Plus

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

Zendy Tools

Zendy Open

We propose the width-resolution mutual learning method (MutualNet) to train anetwork that is executable at dynamic resource constraints to achieve adaptiveaccuracy-efficiency trade-offs at runtime. Our method trains a cohort ofsub-networks with different widths using different input resolutions tomutually learn multi-scale representations for each sub-network. It achievesconsistently better ImageNet top-1 accuracy over the state-of-the-art adaptivenetwork US-Net under different computation constraints, and outperforms thebest compound scaled MobileNet in EfficientNet by 1.5%. The superiority of ourmethod is also validated on COCO object detection and instance segmentation aswell as transfer learning. Surprisingly, the training strategy of MutualNet canalso boost the performance of a single network, which substantially outperformsthe powerful AutoAugmentation in both efficiency (GPU search hours: 15000 vs.0) and accuracy (ImageNet: 77.6% vs. 78.6%). Code is available at\url{https://github.com/taoyang1122/MutualNet}.

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution