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

Structured weight pruning is a representative model compression technique ofDNNs for hardware efficiency and inference accelerations. Previous works inthis area leave great space for improvement since sparse structures withcombinations of different structured pruning schemes are not exploited fullyand efficiently. To mitigate the limitations, we propose SS-Auto, asingle-shot, automatic structured pruning framework that can achieve rowpruning and column pruning simultaneously. We adopt soft constraint-basedformulation to alleviate the strong non-convexity of l0-norm constraints usedin state-of-the-art ADMM-based methods for faster convergence and fewerhyperparameters. Instead of solving the problem directly, a Primal-Proximalsolution is proposed to avoid the pitfall of penalizing all weights equally,thereby enhancing the accuracy. Extensive experiments on CIFAR-10 and CIFAR-100datasets demonstrate that the proposed framework can achieve ultra-high pruningrates while maintaining accuracy. Furthermore, significant inference speeduphas been observed from the proposed framework through actual measurements onthe smartphone.

SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency