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

Filter pruning method introduces structural sparsity by removing selectedfilters and is thus particularly effective for reducing complexity. Previousworks empirically prune networks from the point of view that filter withsmaller norm contributes less to the final results. However, such criteria hasbeen proven sensitive to the distribution of filters, and the accuracy may hardto recover since the capacity gap is fixed once pruned. In this paper, wepropose a novel filter pruning method called Asymptotic Soft Cluster Pruning(ASCP), to identify the redundancy of network based on the similarity offilters. Each filter from over-parameterized network is first distinguished byclustering, and then reconstructed to manually introduce redundancy into it.Several guidelines of clustering are proposed to better preserve featureextraction ability. After reconstruction, filters are allowed to be updated toeliminate the effect caused by mistakenly selected. Besides, various decayingstrategies of the pruning rate are adopted to stabilize the pruning process andimprove the final performance as well. By gradually generating more identicalfilters within each cluster, ASCP can remove them through channel additionoperation with almost no accuracy drop. Extensive experiments on CIFAR-10 andImageNet datasets show that our method can achieve competitive results comparedwith many state-of-the-art algorithms.

Asymptotic Soft Cluster Pruning for Deep Neural Networks