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 has been widely used for neural network compression because ofits enabled practical acceleration. To date, most of the existing filterpruning works explore the importance of filters via using intra-channelinformation. In this paper, starting from an inter-channel perspective, wepropose to perform efficient filter pruning using Channel Independence, ametric that measures the correlations among different feature maps. The lessindependent feature map is interpreted as containing less usefulinformation$/$knowledge, and hence its corresponding filter can be prunedwithout affecting model capacity. We systematically investigate thequantification metric, measuring scheme and sensitiveness$/$reliability ofchannel independence in the context of filter pruning. Our evaluation resultsfor different models on various datasets show the superior performance of ourapproach. Notably, on CIFAR-10 dataset our solution can bring $0.90\%$ and$0.94\%$ accuracy increase over baseline ResNet-56 and ResNet-110 models,respectively, and meanwhile the model size and FLOPs are reduced by $42.8\%$and $47.4\%$ (for ResNet-56) and $48.3\%$ and $52.1\%$ (for ResNet-110),respectively. On ImageNet dataset, our approach can achieve $40.8\%$ and$44.8\%$ storage and computation reductions, respectively, with $0.15\%$accuracy increase over the baseline ResNet-50 model. The code is available athttps://github.com/Eclipsess/CHIP_NeurIPS2021.

CHIP: CHannel Independence-based Pruning for Compact Neural Networks