Pith. sign in

REVIEW 1 cited by

Leveraging Filter Correlations for Deep Model Compression

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1811.10559 v2 pith:OF6DKMSP submitted 2018-11-26 cs.CV cs.LGeess.IVstat.ML

classification cs.CVcs.LGeess.IVstat.ML
keywords filterscompressionmodelapproachdiscardingpaircorrelationsdeep
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise correlations and drops one of the filters from each such pair. However, instead of discarding one of the filters from each such pair na\"{i}vely, the model is re-optimized to make the filters in these pairs maximally correlated, so that discarding one of the filters from the pair results in minimal information loss. Moreover, after discarding the filters in each round, we further finetune the model to recover from the potential small loss incurred by the compression. We evaluate our proposed approach using a comprehensive set of experiments and ablation studies. Our compression method yields state-of-the-art FLOPs compression rates on various benchmarks, such as LeNet-5, VGG-16, and ResNet-50,56, while still achieving excellent predictive performance for tasks such as object detection on benchmark datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures

    cs.LG 2019-08 conditional novelty 6.0 of 10

    A differentiable, scale-invariant sparsity regularizer based on the squared L1/L2 ratio is applied to neural network pruning and is claimed to beat prior L0 and L1 based methods.

Pith tools