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.
Leveraging Filter Correlations for Deep Model Compression
1 Pith paper cite this work. Polarity classification is still indexing.
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.
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
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.