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

Neural network compression empowers the effective yet unwieldy deepconvolutional neural networks (CNN) to be deployed in resource-constrainedscenarios. Most state-of-the-art approaches prune the model in filter-levelaccording to the "importance" of filters. Despite their success, we notice theysuffer from at least two of the following problems: 1) The redundancy amongfilters is not considered because the importance is evaluated independently. 2)Cross-layer filter comparison is unachievable since the importance is definedlocally within each layer. Consequently, we must manually specify layer-wisepruning ratios. 3) They are prone to generate sub-optimal solutions becausethey neglect the inequality between reducing parameters and reducingcomputational cost. Reducing the same number of parameters in differentpositions in the network may reduce different computational cost. To addressthe above problems, we develop a novel algorithm named as COP(correlation-based pruning), which can detect the redundant filtersefficiently. We enable the cross-layer filter comparison through globalnormalization. We add parameter-quantity and computational-cost regularizationterms to the importance, which enables the users to customize the compressionaccording to their preference (smaller or faster). Extensive experiments haveshown COP outperforms the others significantly. The code is released athttps://github.com/ZJULearning/COP.

COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning