HRel: Filter pruning based on High Relevance between activation maps and class labels (2021-12-01T00:00:00.000000Z)

TL;DR

The proposed HRel pruning method outperforms recent state-of-the-art filter pruning methods and the Information Plane dynamics of Information Bottleneck theory is analyzed for various Convolutional Neural Network architectures with the effect of pruning.

Authors

S. Dubey

4 papers

C. Sarvani

1 papers

Mrinmoy Ghorai

1 papers

S. H. Shabbeer Basha

1 papers

TL;DR

Authors

References77 items

Locally Free Weight Sharing for Network Width Search

Deep Model Compression based on the Training History

Channel Pruning Via Gradient Of Mutual Information For Light-Weight Convolutional Neural Networks

Convergence Behavior of DNNs with Mutual-Information-Based Regularization

Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration

On the Information Plane of Autoencoders

DMCP: Differentiable Markov Channel Pruning for Neural Networks

Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning

Deep network compression based on partial least squares

MINT: Deep Network Compression via Mutual Information-based Neuron Trimming

HRank: Filter Pruning Using High-Rank Feature Map

Channel Pruning via Automatic Structure Search

Redundant feature pruning for accelerated inference in deep neural networks

Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels

AutoSlim: Towards One-Shot Architecture Search for Channel Numbers

Structured Pruning of Recurrent Neural Networks through Neuron Selection

COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning

Network Pruning via Transformable Architecture Search

Geometric Estimation of Multivariate Dependency

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

Adaptive Estimators Show Information Compression in Deep Neural Networks

An Information Theoretic View on Learning of Artificial Neural Networks

Leveraging Filter Correlations for Deep Model Compression

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

Estimating Information Flow in Deep Neural Networks

2PFPCE: Two-Phase Filter Pruning Based on Conditional Entropy

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation

Understanding Convolutional Neural Networks With Information Theory: An Initial Exploration

Compressing Neural Networks using the Variational Information Bottleneck

On the information bottleneck theory of deep learning

Scalable Mutual Information Estimation Using Dependence Graphs

Mutual Information Neural Estimation

Fruit recognition from images using deep learning

Analyzing bin-width effect on the computed entropy

Learning Efficient Convolutional Networks through Network Slimming

Evaluating deep learning architectures for Speech Emotion Recognition

ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

Estimating Mixture Entropy with Pairwise Distances

Opening the Black Box of Deep Neural Networks via Information

YOLO9000: Better, Faster, Stronger

Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

Pruning Filters for Efficient ConvNets

Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures

Nesterov's accelerated gradient and momentum as approximations to regularised update descent

Quantized Convolutional Neural Networks for Mobile Devices

Deep Residual Learning for Image Recognition

Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

Deep Colorization

BinaryConnect: Training Deep Neural Networks with binary weights during propagations

Learning both Weights and Connections for Efficient Neural Network

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Distilling the Knowledge in a Neural Network

FitNets: Hints for Thin Deep Nets

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Speeding up Convolutional Neural Networks with Low Rank Expansions

Measures of Entropy From Data Using Infinitely Divisible Kernels

Quantum Computation and Quantum Information

Nonnegative Decomposition of Multivariate Information

A class of Rényi information estimators for multidimensional densities

Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)

Elements of Information Theory

Result Analysis of the NIPS 2003 Feature Selection Challenge

Estimating mutual information.

The information bottleneck method

Multivariate Extension of Matrix-Based Rényi's $\alpha$α-Order Entropy Functional

IJCNN

MNIST handwritten digit database

Learning Multiple Layers of Features from Tiny Images

Cover and Joy

Shiv Ram Dubey, and Snehasis Mukherjee

Monographs on statistics and applied probability

Optimal Brain Damage

Accepted version of article