Domino Saliency Metrics: Improving Existing Channel Saliency Metrics with Structural Information

05/04/2022
by   Kaveena Persand, et al.
0

Channel pruning is used to reduce the number of weights in a Convolutional Neural Network (CNN). Channel pruning removes slices of the weight tensor so that the convolution layer remains dense. The removal of these weight slices from a single layer causes mismatching number of feature maps between layers of the network. A simple solution is to force the number of feature map between layers to match through the removal of weight slices from subsequent layers. This additional constraint becomes more apparent in DNNs with branches where multiple channels need to be pruned together to keep the network dense. Popular pruning saliency metrics do not factor in the structural dependencies that arise in DNNs with branches. We propose Domino metrics (built on existing channel saliency metrics) to reflect these structural constraints. We test Domino saliency metrics against the baseline channel saliency metrics on multiple networks with branches. Domino saliency metrics improved pruning rates in most tested networks and up to 25

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/03/2020

Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle

The computation and memory needed for Convolutional Neural Network (CNN)...
research
10/30/2016

Compact Deep Convolutional Neural Networks With Coarse Pruning

The learning capability of a neural network improves with increasing dep...
research
07/12/2022

Rethinking gradient weights' influence over saliency map estimation

Class activation map (CAM) helps to formulate saliency maps that aid in ...
research
09/07/2022

Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps

Convolutional Neural Networks (CNNs) compression is crucial to deploying...
research
04/06/2020

There and Back Again: Revisiting Backpropagation Saliency Methods

Saliency methods seek to explain the predictions of a model by producing...
research
03/04/2023

Visual Saliency-Guided Channel Pruning for Deep Visual Detectors in Autonomous Driving

Deep neural network (DNN) pruning has become a de facto component for de...

Please sign up or login with your details

Forgot password? Click here to reset